cn_media 大模型/产品 IT之家
一加 Watch 4 智能手表包装曝光
IT之家 4 月 17 日消息，消息源 @erenylmaz075 于 4 月 15 日在 X 平台发布推文，分享了一组包装图片，展示了一加 Watch 4， 并透露该智能手表型号为 OPWWE261。
AI 资讯、招聘与订阅源
Claude Opus 4.7 在盲测中以 69:31 击败 4.6 版本；Meta 发布 Muse Spark 转向闭源策略；AWS Bedrock 支持按 IAM 主体归因推理成本。
智谱AI旗下AutoClaw（澳龙）正式上线自进化机制与Skill商店。自进化功能可自动识别用户纠正、偏好及失败教训，经审批后固化为永久记忆，实现Agent越用越懂用户。平台同步推出GLM Office Skills五件套，基于GLM-5.1支持PPT、Word等细分场景设计、智能自检与格式互转，可一键生成配套办公材料。来源：智谱...
MiniMax正式推出全球首个云端沙箱Hermes——MaxHermes，基于Hermes Agent构建的云端自我进化AI助手。产品核心创新为学习闭环机制：每完成复杂任务自动提炼可复用的Skills能持续自我迭代，配备持久化记忆与多子代理并行能力。产品零门槛部署，已打通飞书、钉钉、企业微信等IM渠道，支持Token Plan抵扣消耗。来源：MiniMax 稀宇科技...
IT之家 4 月 17 日消息，消息源 @erenylmaz075 于 4 月 15 日在 X 平台发布推文，分享了一组包装图片，展示了一加 Watch 4， 并透露该智能手表型号为 OPWWE261。
IT之家 4 月 17 日消息，鸿蒙智行今日官宣， 问界 M6 车型预售订单突破 10 万，官方现推出甄选现车，提前发运全国门店。 提前锁定甄选现车资源，最快可 1 周内提车 。
IT之家 4 月 17 日消息，为纪念红军长征胜利 90 周年， 我国战争 / 历史类型电影《四渡》昨日官宣定档 6 月 26 日上映 ，并发布了“出奇制胜”版定档预告。 纪念红军长征胜利 90 周年，再现四渡赤水经典战例。
IT之家 4 月 17 日消息，据央视新闻报道，4 月 17 日 12 时 10 分，我国在酒泉卫星发射中心使用长征四号丙运载火箭， 成功将高精度温室气体综合探测卫星发射升空 ，卫星顺利进入预定轨道，发射任务取得圆满成功。 IT之家注意到，这次任务是长征系列运载火箭的第 638 次飞行。
IT之家 4 月 17 日消息，博主 @数码闲聊站 今天午间爆料称，绿厂（OPPO）的云台相机项目内部“今天开工会了”，该项目代号为“扶摇”，寓意“扶摇直上”， 大概率年内发布 ，目前保密程度“很高”。 评论区中，该博主进一步表示，这款产品将 对标大疆 Pocket 系列 ，“相信手机厂商的卷法吧。
IT之家 4 月 17 日消息，科技媒体 photorumors 昨日（4 月 16 日）发布博文，报道称在下周举办的 NAB 展会上， 唯卓仕（Viltrox）将会发布 AF 35mm f/1.8 与 AF 55mm f/1.8 两款 EVO APO 全画幅镜头。
IT之家 4 月 17 日消息，华为官方今日公布了 WATCH GT 6 Pro 手表的 HarmonyOS 6.0 版本升级的一图览。本次更新带来全新个性化表盘，同时新增多项运动相关功能。
IT之家 4 月 17 日消息，据新浪电影今日报道，在今日的第 16 届北京国际电影节产业论坛上，爱奇艺创始人、CEO 龚宇谈到了影视行业的开源节流。 龚宇表示， 现在制作成本太高，无论是电影还是电视剧，成本太高了，亏损是大概率盈利是小概率的 ，剧集方面低了说 30% 挣钱，高了说 40% 挣钱，大部分都是亏损的。
IT之家 4 月 17 日消息，今天午间，据彭博社报道，负责 Apple Watch、AirPods、健康与智能家居业务的苹果营销高管斯坦 · 吴宣布退休，这一变动涉及多条核心产品线。 在苹果任职 31 年的斯坦 · 吴正式离职。在任期间，他参与初代 Apple Watch 的构思，并持续参与后续产品及相关配件的发展。
IT之家 4 月 17 日消息，当地时间 4 月 15 日，据外媒 ZDNet 报道，盖洛普发布的最新报告称，目前约一半员工每年至少会在工作中使用几次 AI，高于上一季度的 46%，创下该机构统计以来的最高水平。
IT之家 4 月 17 日消息，在国务院新闻办公室今天举行的“开局起步‘十五五’”系列主题新闻发布会上，国家发展改革委副主任王昌林表示，“十五五”时期将实施非化石能源十年倍增行动，加快推进新型能源体系建设。
IT之家 4 月 17 日消息，博主 @数码闲聊站 今日曝光了一款 10000mAh 级超大电池的手机： 独家， 子系中端线会率先上 10000mAh 级超大电池 、100W 闪充、2 亿大底主摄、金属中框、光学指纹、1.
IT之家 4 月 17 日消息，微星 (MSI) 现已在官网上线 VERSA 300 WIRELESS 8K，这是 该企业首款支持 8kHz 回报率的鼠标产品 。该型号搭载原相 PAW3395 光学传感器和 60M 欧姆龙微动，重 66g，兼容 MSI PortalX 网页驱动。
Article URL: https://www.theverge.com/tech/913638/bluesky-has-been-dealing-with-a-ddos-attack-for-nearly-a-full-day Comments URL: https://news.ycombinator.
IT之家 4 月 17 日消息，科技媒体 Ars Technica 今天（4 月 17 日）发布博文，报道称 美国宇航局（NASA）确认 SpaceX 猎鹰重型火箭将发射欧空局（ESA）的“罗莎琳德 · 富兰克林”（Rosalind Franklin）火星车，预计 2028 年底升空、2030 年抵达火星。
IT之家 4 月 17 日消息，近日，市场监管总局联合公安部开展传统工艺市场“打假清源”联合执法行动，深入整治传统工艺市场“ 假证书、假机构、假产品、假网站 ”等突出问题，并在总局官网首页开通传统工艺市场“打假清源”举报渠道，广泛搜集相关违法违规案件线索。
IT之家 4 月 17 日消息，字节跳动官方昨日宣布，正式启动前沿技术领域人才校园招聘。 据介绍，前沿技术领域人才校招是字节跳动面向全球优秀技术人才推出的招聘项目，涵盖全职和实习生招聘，开放大模型应用、搜索 / 推荐 / 广告、计算机体系结构与系统优化、安全 / AI Safety、硬件、AI Coding、AIGC、...
IT之家 4 月 17 日消息，神牛今日宣布，iT30Pro 闪光灯新增徕卡 L 口版本，售价 588 元 。 这款闪光灯重 120 克，支持 TTL 自动闪光，提供 1/8000s 高速同步，配备全彩触摸屏，同时也配备传统旋转拨盘进行操作。
IT之家 4 月 17 日消息，据澎湃新闻报道，国家发展改革委低空经济发展司司长郑剑 4 月 17 日在国新办“开局起步‘十五五’”系列主题新闻发布会上表示，近期我们也注意到，社会舆论反映存在无人机飞行活动审批难的问题。
IT之家 4 月 17 日消息，智谱今日宣布 AutoClaw（澳龙）正式上线自进化机制与 Skill 商店，踩过一次坑，下次同类任务会直接走正确流程。 官方介绍称，在使用龙虾等 Agent 时，许多人会感到 Agent 很“健忘”，需要反复提醒类似的要求：“简洁点”、“参考 XX 的风格”、“不要用破折号”…… 然而...
IT之家 4 月 17 日消息，佳翼 (JEYI) 昨日展示了其新开发的平装版 ArcherX PCIe 转 M.2 扩展卡。与一般垂直于主板的 PCIe 转 M.2 设备不同，该扩展卡的 M.2 插槽与主板平行， 可利用被多槽显卡遮挡的空闲 PCIe ， 适合紧凑装机环境 。
IT之家 4 月 17 日消息，国新办 4 月 17 日举行“开局起步‘十五五’”系列主题新闻发布会，国家发展改革委产业发展司司长傅久岭表示， 智能化的目的是提升效率，不是简单替代劳动者，要找准政策平衡点 。 傅久岭表示，“十五五”时期，构建以先进制造业为骨干的现代化产业体系是重中之重。
IT之家 4 月 17 日消息，今天上午，华为常务董事、产品投资委员会主任、终端 BG 董事长余承东在微博发文预热鸿蒙智行首款 MPV 车型 —— 智界 V9。 据其介绍，这款“黑科技拉满”的新车将搭载森林级车载制氧系统，支持全舱供氧，提供弥散 + 鼻吸两种供氧模式。
IT之家 4 月 17 日消息，在今日的 2026 智元合作伙伴大会上， 智元发布 358 宏图计划 ，推动具身生产力落地。 智元创始人、董事长兼 CEO 邓泰华表示： 2025 年（智元成立 3 年）智元已实现 10 亿元营收，实现生产力入门，开启第一曲线；
Article URL: https://blog.discourse.org/2026/04/discourse-is-not-going-closed-source/ Comments URL: https://news.ycombinator.
IT之家 4 月 17 日消息，科技媒体 TechPowerUp 今天（4 月 17 日）发布博文，报道称 Valve 推出 Proton 11 Beta 兼容层， 重点改进游戏性能，并支持 Steam Frame 独立 VR 头显。
IT之家 4 月 17 日消息，4 月 16 日，东鹏特饮宣布正式成为张雪机车 WSBK 全球冠名合作品牌。在活动现场， 张雪承诺 3 年内拿 1 个年度总冠军 ，回报东鹏。给网友送 500 顶签名帽 +5 个现场观赛名额，所有费用张雪机车承担。 IT之家注意到，张雪机车在 WSBK 葡萄牙站夺得冠军后，引发极大关注。
只要选对豆子、控制好手冲时的变量，一杯好咖啡也很简单。 查看全文
IT之家 4 月 17 日消息，社交媒体上今日有多位网友发布视频称，在高德地图楼下遇到 高德机器狗过马路和买奶茶 。从视频中看到，机器狗身上印有高德地图 logo。 高德相关负责人日前表示，高德已在具身智能领域开展深入布局，并积极探索四足机器人、人形机器人等硬件产品形态， 预计近期将有首款四足机器人发布 。
IT之家 4 月 17 日消息，小米官方今日宣布，REDMI Book 2026 笔记本开售，4 月 23 日前购机直降 500 元，到手价 5499 元起 ： REDMI Book 14 2026 16GB+512GB：5499 元 16GB+1TB：5999 元 32GB+1TB：6499 元 京东 小米 REDM...
IT之家 4 月 17 日消息，科技媒体 computerbase 昨日（4 月 16 日）发布博文，报道称针对安全研究员 @weezerOSINT 指控 GPU-Z 存在严重安全漏洞一事， 开发者 Wizzard 回应称报告部分内容失实，强调普通用户根本无法直接访问驱动程序，必须持有管理员权限方可执行相关操作。
IT之家 4 月 17 日消息，今天上午，vivo 手机官微预告旗下新机：vivo Y600 Pro。海报显示，这款手机将拥有 5000 万像素镜头，并采用双摄布局。此外，这款新机将主打“万级长续航”，预计其电池容量可达 10000mAh 。
IT之家 4 月 17 日消息，据央视新闻今日报道，从国家标准委了解到，我国在国际标准化组织成功立项 具身智能领域全球首项国际标准《人形机器人数据集》 ，并推动成立了首个由我国专家担任召集人的工作组。
IT之家 4 月 17 日消息，科技媒体 Notebook Check 今天（4 月 17 日）发布博文，分享影石 Insta360 Luna Ultra 相关图片， 这款双摄手持云台相机预估配备 6 倍光学变焦镜头和可拆卸云台设计，上市后将会和大疆 Osmo Pocket 4P 正面竞争。
IT之家 4 月 17 日消息，今天上午，一汽-大众官方公众号发文宣布，捷达品牌概念车 JETTA X 将在 4 月 21 日的大众汽车集团媒体之夜 活动中正式亮相。从预告图的轮廓中可以看出，新车预计是一款 SUV 或跨界车型，并将采用电动化的动力，不过究竟是纯电还是插混暂未可知。
IT之家 4 月 17 日消息，小牛电动今日发布了小牛 N One 电动摩托车，4 月 17 日 19:00 正式开售， 新品一口价 2999 元 。 小牛 N One 有深空灰、星空黑、珍珠白三种颜色可选； 电机峰值功率 1800W，极速 47km/h ；
IT之家 4 月 17 日消息，Thermaltake（曜越）现已上架 TR300 系列 ATX 机箱。这一型号可分为 TG 常规和 WS 实木饰条前面板两种版本， TR300 TG 售价 599 元 、 TR300 WS 售价 699 元 ；额外的 6" 1480×720 LCD 扩展配件则是 749 元。
IT之家 4 月 17 日消息，科技媒体 Android Headline 昨日（4 月 16 日）发布博文，分享了一组渲染图，展示了三星 Galaxy A27 手机。外观方面， 该机最大变化就是摒弃以往前摄与边框融合方案，改用打孔屏设计。
IT之家 4 月 17 日消息，春风动力今日官宣 800MT-ES 摩托车上市，价格为 53980 元。新车全新搭载 ISS 智能悬挂系统，前后双电子减震全域精准适配，集成阻尼随速调节、起步防翘头、制动防翘尾、跳跃抑制多种功能。
Article URL: https://www.ycombinator.com/companies/substrate/jobs/QJU9023-harness-engineer Comments URL: https://news.ycombinator.
IT之家 4 月 17 日消息，希未 (SEAVIV) 昨日宣布 AideaMini R3 Max 迷你主机即将上市。这一型号基于 AMD 锐龙 AI 9 HX 470 "Gorgon Point" 处理器，支持 45W / 54W / 65W 三档性能释放。
IT之家 4 月 17 日消息，2026 款极核 AE4 电动摩托车今日正式发布， 首发权益价 5699 元起 。 该车首发可享 10 大权益，包括赠送手机支架、加赠 12 个月车联网服务、至高减免 400 元区域服务费、车架终身质保等。
Article URL: https://reclaimthenet.org/us-bill-mandates-on-device-age-verification Comments URL: https://news.ycombinator.
IT之家 4 月 17 日消息，美国比价、回收平台 SellCell 昨日（4 月 16 日）发布博文，调查美国超过 5000 名智能手机用户后， 发现苹果 iPhone 用户忠诚度达到 96.4%，安卓手机忠诚度达 86.4%。
IT之家 4 月 17 日消息，一加今日宣布一加 Ace6 至尊版下周见，号称“九亿少年的梦想装备”。从预热内容来看，该机将主打游戏性能，在操控上带来不同体验。 新机的「王牌觉醒」配色已经公布，大面积使用深邃暗色辅以 3D 立体刻光工艺，在机身上“雕刻”出了 Ace 的品牌标识。
IT之家 4 月 17 日消息，博主 @数码闲聊站 今日曝光了 联发科天玑 9600 Pro（暂定名） 的跑分信息。 该处理器采用台积电 N2p 工艺打造，双超大核高频近 5GHz，目前 ES 样片早期设计指标（估分）是 GB6 单核 4200-4300±，多核 12000-12500± 。
今年以来，OpenClaw 掀起的“养龙虾”热潮属实是火出圈了，许多用户涌入尝试打造属于自己的 AI 执行体，但热潮背后，痛点也随之暴露：复杂的环境部署、繁琐的参数配置、任务执行易中断、设备间数据割裂，让不少普通用户望而却步，最终只能止步于“看着好玩，用着费劲”的阶段。
IT之家 4 月 17 日消息，小米米家高速水离子吹风机 Pro 预售今日开启，升级 12 万转 / 分钟高速马达，定价 799 元，京东小米官方旗舰店券后 719.1 元。 该吹风机可选薄暮金、雾凇紫、鸢尾蓝三种配色，其采用金属珠光漆机身，带有一块彩色屏幕，握柄处提供铝合金调温旋钮，拥有一定质感。
IT之家 4 月 17 日消息，智元 2026 合作伙伴大会于今日上午在上海开幕。智元创始人、董事长兼 CEO 邓泰华表示， 智元 2025 年度营收达 10.5 亿元 ，“我们成为国内最快实现 10 亿营收的机器人公司”。 邓泰华透露，2026 年智元营收目标为进一步实现数倍增长。
IT之家 4 月 17 日消息，北京时间今日凌晨，《地铁》系列游戏最新作品《Metro 2039（地铁 2039）》正式发布了其首支预告片。 IT之家了解到，本作由开发商 4A Games 打造， 将于 2026 年冬季登陆 Xbox Series X|S 主机与 PC 平台 ，支持 XPA。
IT之家 4 月 17 日消息，市场调查机构 CounterPoint Research 昨日（4 月 16 日）发布博文，报道称由于 2025 年下半年内存价格飙升，全球智能手机行业成本压力剧增， 150 美元以下低端机型销量同比下滑 11%，ODM / IDH 设计机型出货量下降 10%，结束连续两年增长。
IT之家 4 月 17 日消息，当地时间 4 月 16 日，据路透社报道，在油价上涨背景下，德国消费者对电动汽车的兴趣明显提升，比亚迪等中国品牌正加速获得关注。 Carwow 数据显示，比亚迪今年第一季度在德国的 购车咨询量同比增长 135% ，成为增长最快的品牌之一，消费者对旗下纯电 SUV 及海豚等入门车型表现出较...
IT之家 4 月 17 日消息，小佩发布了智能宠物饮水机 ULTRA（可视版），将于 4 月 22 日开始预售， 售价 799 元 。 这款产品搭载 140° 超广角摄像头 ，宠物喝水全程看得见，支持远程操控、语音互动等；支持 AI 识别多宠面部 ，猫脸 / 狗脸均可识别；
IT之家 4 月 17 日消息，HP（惠普）旗下游戏电竞品牌 HyperX（极度未知）本周启动了 2026 款暗影精灵 (OMEN) 游戏本产品的预热，其中 15 日介绍了 PRO 15" 机型、16 日则介绍了 PRO 16"。
IT之家 4 月 17 日消息，致态 TiPlus 系列首款 PCIe 5.0 旗舰产品 —— TiPlus9100 固态硬盘 今日正式发布。 TiPlus9100 搭载长江存储晶栈 Xtacking 4.0 架构闪存颗粒，可兼容游戏本、轻薄本、DIY 台式机等各类设备。
IT之家 4 月 17 日消息，科技媒体 BornCity 今天（4 月 17 日）发布博文，微软在 17 个小时内， 紧急修复 Chrome 147 浏览器无法正常使用 Microsoft 365 服务问题。
IT之家 4 月 17 日消息，大脑皮层，这个掌管感觉、运动和高级认知的“总指挥部”，它的起源究竟是哪里？ 学界长期存在两种截然不同的理论推测： 双重起源假说 认为皮层源于海马和梨状皮层两类古老的异皮层，通过渐进层状分化向外扩张。
IT之家 4 月 17 日消息，据日经亚洲 4 月 15 日报道，日本新干线即将推出新一代私人包厢，配备 定向声场座椅和内嵌 5G 天线车窗 等技术，以提升私密性与网络体验。 该服务将于 10 月在 JR 东海运营的东海道新干线上上线。
IT之家 4 月 17 日消息，美国载人绕月计划“阿尔忒弥斯 2 号”（Artemis II）宇航员于 4 月 10 日返回地球后，于 4 月 16 日召开新闻发布会，分享深空飞行体验。
IT之家 4 月 17 日消息，据央视新闻今日报道，我国在国际标准化组织成功立项 具身智能领域全球首项国际标准《人形机器人数据集》 ，并推动成立了首个由我国专家担任召集人的工作组。 报道称，当前，美国、日本、欧盟等主要经济体都将人形机器人纳入国家科技战略，争相布局研发与应用。
IT之家 4 月 17 日消息，联想集团昨日宣布，位于 沙特阿拉伯首都利雅得 的中东、土耳其及非洲 （META）区域总部 近日正式启用。 位于利雅得的区域总部将作为联想集团推进中东、土耳其及非洲区域战略与运营的核心平台，覆盖以上市场。这也是联想集团与沙特公共投资基金（PIF）旗下公司 Alat 埃耐特战略合作的一部分。
IT之家 4 月 17 日消息，Keychron 渴创现已推出 G4 三模鼠标。这一型号外观方面采用复古配色， 灰白色的主体上点缀以红色零部件 ，底部的切换键拥有像素锯齿轮廓，定价 79.99 美元（IT之家注：现汇率约合 546.7 元人民币）。
IT之家 4 月 17 日消息，当地时间 4 月 16 日，据外媒 TechSpot 报道，美国北卡罗来纳州立大学与休斯敦大学的研究团队开发出一种 可反复自修复的纤维增强复合材料 ，修复次数 可超过 1000 次 ，且强度高于现有航空级复合材料。
IT之家 4 月 17 日消息，IT之家从国家市场监督管理总局获悉，日前，浙江吉利汽车有限公司根据《缺陷汽车产品召回管理条例》和《缺陷汽车产品召回管理条例实施办法》的要求，向国家市场监督管理总局备案了召回计划。
IT之家 4 月 17 日消息，源杰科技今日（4 月 17 日）上午持续走强，股价突破 1410 元， 盘中超越贵州茅台成为 A 股新“股王” 。 2024 年 9 月 24 日至今，贵州茅台累计涨幅近 20%，源杰科技累计涨幅近 1500%。
OpenAI 升级 Codex 新增多项实用功能，大疆发布 Osmo Pocket 4 云台相机等。 查看全文
I built MCP servers for my oscilloscope and SPICE simulator so Claude Code can close the loop between simulation and real hardware. Comments URL: https://news.
Article URL: https://techcrunch.com/2026/04/16/everything-we-like-is-a-psyop/ Comments URL: https://news.ycombinator.
Article URL: https://www.theguardian.com/us-news/ng-interactive/2026/apr/16/amazon-price-fixing-california-lawsuit Comments URL: https://news.ycombinator.
Article URL: https://github.com/gainsec/autoprober Comments URL: https://news.ycombinator.com/item?id=47800033 Points: 133 # Comments: 26
Article URL: https://ropensci.org/blog/2026/04/02/tree-sitter-overview/ Comments URL: https://news.ycombinator.com/item?id=47799573 Points: 110 # Comments: 11
Article URL: https://tomtunguz.com/ai-compute-crisis-2026/ Comments URL: https://news.ycombinator.com/item?id=47799322 Points: 35 # Comments: 54
Article URL: https://www.joanwestenberg.com/the-passive-income-trap-ate-a-generation-of-entrepreneurs/ Comments URL: https://news.ycombinator.
Article URL: https://arxiv.org/abs/2604.12040 Comments URL: https://news.ycombinator.com/item?id=47798875 Points: 6 # Comments: 2
Article URL: https://clojure.org/about/documentary Comments URL: https://news.ycombinator.com/item?id=47798345 Points: 135 # Comments: 37
Article URL: https://openai.com/index/introducing-gpt-rosalind/ Comments URL: https://news.ycombinator.com/item?id=47798244 Points: 80 # Comments: 20
Article URL: https://news.play.date/news/duke-playdate-education/ Comments URL: https://news.ycombinator.com/item?id=47798176 Points: 108 # Comments: 44
Article URL: https://android-developers.googleblog.com/2026/04/build-android-apps-3x-faster-using-any-agent.html Comments URL: https://news.ycombinator.
Article URL: https://simonwillison.net/2026/Apr/16/qwen-beats-opus/ Comments URL: https://news.ycombinator.com/item?id=47796830 Points: 353 # Comments: 76
Article URL: https://openai.com/index/codex-for-almost-everything/ Comments URL: https://news.ycombinator.com/item?id=47796469 Points: 773 # Comments: 390
Hey HN, In this age of agentic coding I've found myself spending a lot of time reviewing markdown files.
Hey! I am Alex and together with my co-founder Tarun built Kampala ( https://www.zatanna.ai/kampala ).
The updated Codex app for macOS and Windows adds computer use, in-app browsing, image generation, memory, and plugins to accelerate developer workflows.
前言工作的疲惫和生活中琐事积压，让我产生了换个环境去旅居的念头，最近在积极的考察一些比较宜居的城市。四月初趁着出差的机会来到了福建和广西，边应付公司的事物边考察当地的宜居城市。我先去了厦门，之后从南宁 ... 查看全文
当代城市工作者的出行场景正变得越来越复合。人们希望在一个背包里装下工作所需的电脑与数码设备，同时塞入下班健身的衣物，甚至直接背着它开启一趟两三天的短途差旅。但要在同一个背包上同时实现「出色的设备保护」 ... 查看全文
这份坚守，无关情怀的浪漫，而在于技术的胜利。 查看全文
Apple 成功地在一个操作系统版本中集齐了图标设计中的常见错误。 查看全文
OpenAI introduces GPT-Rosalind, a frontier reasoning model built to accelerate drug discovery, genomics analysis, protein reasoning, and scientific research wor...
OpenAI 推出网络安全专用模型 GPT-5.4-Cyber、索尼宣布将调整 Bravia 电视的功能等。 查看全文
Leading security firms and enterprises join OpenAI’s Trusted Access for Cyber, using GPT-5.4-Cyber and $10M in API grants to strengthen global cyber defense.
Our newest audio model introduces granular audio tags that give you precise control to direct AI speech for expressive audio generation.
Windows预览体验计划的新变化@广陵止息：我们在4月13日的早报中详细介绍了Windows预览体验计划的新变化，总体来看是好事，所以这里就不再赘述了。在本期具透Plus中我想聊聊Windows、m ... 查看全文 本文为会员文章，出自 《单篇文章》 ，订阅后可阅读全文。
OpenAI updates the Agents SDK with native sandbox execution and a model-native harness, helping developers build secure, long-running agents across files and to...
本文首发于「游研社」，作者@Oracle，少数派经授权转载，仅对排版略作调整。阅读原文在发售前后的48小时内，《红色沙漠》故事几乎就已经被写好了：3月18日，游戏上市前的宣发预热达到顶点时，媒体评分解 ... 查看全文
什么 Liquid Glass？我只喜欢 Windows Aero。 查看全文
arXiv:2604.14160v1 Announce Type: new Abstract: The rapid digitization of nuclear power plant main control rooms has fundamentally reshaped operator interaction...
arXiv:2604.14178v1 Announce Type: new Abstract: Large Language Model (LLM) agents have demonstrated remarkable capabilities in reasoning and tool use, yet they...
arXiv:2604.14221v1 Announce Type: new Abstract: Reliable evaluation of anomaly detection methods in multivariate time series remains an open challenge, largely...
arXiv:2604.14240v1 Announce Type: new Abstract: The simulation of complex systems increasingly relies on sophisticated but fundamentally opaque computational bl...
arXiv:2604.14254v1 Announce Type: new Abstract: The field of machine ethics aims to build Artificial Moral Agents (AMAs) to better understand morality and make...
arXiv:2604.14258v1 Announce Type: new Abstract: Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (...
arXiv:2604.14316v1 Announce Type: new Abstract: Large scale vision language models have shown promise in automating chest Xray interpretation, yet their clinica...
arXiv:2604.14336v1 Announce Type: new Abstract: Synaptic plasticity is metabolically expensive, yet animals continuously update their internal models without ex...
arXiv:2604.14401v1 Announce Type: new Abstract: Agentic AI systems are becoming commonplace in domains that require long-lived, stateful decision-making in cont...
arXiv:2604.14419v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) architectures employ increasingly sophisticated routing mechanisms -- learned ro...
arXiv:2604.14422v1 Announce Type: new Abstract: Data analysts working with relational data often start with vague or underspecified questions and refine them it...
arXiv:2604.14434v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models scale parameters while fixing active computation per token, but the speci...
arXiv:2604.14440v1 Announce Type: new Abstract: We propose a Reinforcement Learning (RL) based control design framework for handling complex tasks.
arXiv:2604.14455v1 Announce Type: new Abstract: AI models underpin modern intelligent systems, driving advances across science, medicine, finance, and technolog...
arXiv:2604.14465v1 Announce Type: new Abstract: AI systems are increasingly used to assist humans in sequential decision-making tasks, yet determining when and...
arXiv:2604.14473v1 Announce Type: new Abstract: A common approach to personalization in large language models (LLMs) is to incorporate a subset of the user memo...
arXiv:2604.14475v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents can orchestrate specialist classifiers, segmentation models, an...
arXiv:2604.14477v1 Announce Type: new Abstract: Transparency of neural networks' internal reasoning is at the heart of interpretability research, adding to trus...
arXiv:2604.14493v1 Announce Type: new Abstract: Deploying high-quality automatic speech recognition (ASR) on edge devices requires models that jointly optimize...
arXiv:2604.14498v1 Announce Type: new Abstract: Synthetic augmentation is increasingly used to mitigate data scarcity in financial machine learning, yet its sta...
arXiv:2604.14500v1 Announce Type: new Abstract: Expert specialization is fundamental to Mixture-of-Experts (MoE) model success, yet existing metrics (cosine sim...
arXiv:2604.14514v1 Announce Type: new Abstract: Healthcare disparities persist across socioeconomic boundaries, often attributed to unequal access to screening,...
arXiv:2604.14518v1 Announce Type: new Abstract: We present \textbf{Mind DeepResearch (MindDR)}, an efficient multi-agent deep research framework that achieves l...
arXiv:2604.14525v1 Announce Type: new Abstract: Large language models frequently produce mutually inconsistent answers when reasoning over multiple related quer...
arXiv:2604.14528v1 Announce Type: new Abstract: Large Language Models (LLMs) achieve strong performance through extended inference-time deliberation, yet how th...
arXiv:2604.14531v1 Announce Type: new Abstract: Every call to an LLM classification endpoint produces a labeled input-output pair already retained in production...
arXiv:2604.14564v1 Announce Type: new Abstract: Reinforcement learning (RL) paradigms have demonstrated strong performance on reasoning-intensive tasks such as...
arXiv:2604.14576v1 Announce Type: new Abstract: Large language models (LLMs) show promise in generating supportive responses for mental health and counseling ap...
arXiv:2604.14585v1 Announce Type: new Abstract: Prompt optimization in compound AI systems is statistically indistinguishable from a coin flip: across 72 optimi...
arXiv:2604.14607v1 Announce Type: new Abstract: We study the overall process of automatic formalization of GDPR provisions using large language models, within a...
arXiv:2604.14609v1 Announce Type: new Abstract: AI for science promises to accelerate the discovery process.
arXiv:2604.14615v1 Announce Type: new Abstract: Scientific discovery in digital health requires converting continuous physiological signals from wearable device...
arXiv:2604.14627v1 Announce Type: new Abstract: The exact cover problem is a classical NP-hard problem with broad applications in the area of AI.
arXiv:2604.14641v1 Announce Type: new Abstract: When faced with complex spatial problems, humans naturally sketch layouts to organize their thinking, and the ac...
arXiv:2604.14646v1 Announce Type: new Abstract: Recent advances in reinforcement learning (RL) have improved the reasoning capabilities of large language models...
arXiv:2604.14655v1 Announce Type: new Abstract: We present AgentGA, a framework that evolves autonomous code-generation runs by optimizing the agent seed: the t...
arXiv:2604.14656v1 Announce Type: new Abstract: Most medical multimodal benchmarks focus on static tasks such as image question answering, report generation, an...
arXiv:2604.14682v1 Announce Type: new Abstract: Speculative decoding accelerates large language model (LLM) inference.
arXiv:2604.14683v1 Announce Type: new Abstract: Deep Research Agents (DRAs) aim to solve complex, long-horizon research tasks involving planning, retrieval, mul...
arXiv:2604.14687v1 Announce Type: new Abstract: Monte-Carlo Tree Search (MCTS) is a fundamental sampling-based search algorithm widely used for online planning...
arXiv:2604.14691v1 Announce Type: new Abstract: LLM-empowered agent simulations are increasingly used to study social emergence, yet the micro-to-macro causal m...
arXiv:2604.14705v1 Announce Type: new Abstract: Human activity traces (HATs) are critical for many applications, including human mobility modeling and point-of-...
arXiv:2604.14709v1 Announce Type: new Abstract: Existing benchmarks for hardware design primarily evaluate Large Language Models (LLMs) on isolated, component-l...
arXiv:2604.14712v1 Announce Type: new Abstract: LLM-powered systems require complex multi-step decision-making abilities to solve real-world tasks, yet current...
arXiv:2604.14717v1 Announce Type: new Abstract: Persistent language-model agents increasingly combine tool use, tiered memory, reflective prompting, and runtime...
arXiv:2604.14718v1 Announce Type: new Abstract: This article argues that the most important significance of the AI revolution, especially the rise of large lang...
arXiv:2604.14738v1 Announce Type: new Abstract: Consumer wearables enable continuous measurement of physiological data related to stress and recovery, but turni...
arXiv:2604.14746v1 Announce Type: new Abstract: Conventional Graph Contrastive Learning (GCL) on Text-Attributed Graphs (TAGs) relies on blind stochastic augmen...
arXiv:2604.14768v1 Announce Type: new Abstract: Large Language Models (LLMs) exhibit strong mathematical reasoning when trained on high-quality Chain-of-Thought...
arXiv:2604.14785v1 Announce Type: new Abstract: Recent progress in Multimodal Large Language Models (MLLMs) has demonstrated remarkable advances in perception a...
arXiv:2604.14786v1 Announce Type: new Abstract: Generative Agents, owing to their precise modeling and simulation capabilities of human behavior, have become a...
arXiv:2604.14788v1 Announce Type: new Abstract: Developing an MR sequence is challenging and remains largely constrained by human intuition.
arXiv:2604.14789v1 Announce Type: new Abstract: Deploying deep neural networks on edge devices requires balancing accuracy, latency, and resource constraints un...
arXiv:2604.14790v1 Announce Type: new Abstract: Interactive Evolutionary Computation (IEC) provides a powerful framework for optimizing subjective criteria such...
arXiv:2604.14807v1 Announce Type: new Abstract: The rapid integration of large language models (LLMs) into everyday workflows has transformed how individuals pe...
arXiv:2604.14829v1 Announce Type: new Abstract: Evaluating large language models (LLMs) for clinical documentation tasks such as SOAP note generation remains ch...
arXiv:2604.14838v1 Announce Type: new Abstract: Current single-cell foundation model benchmarks universally extract final layer embeddings, assuming these repre...
arXiv:2604.14847v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chains of thought but...
arXiv:2604.14858v1 Announce Type: new Abstract: As agent systems move into increasingly diverse execution settings, trajectory-level safety evaluation and diagn...
arXiv:2604.14881v1 Announce Type: new Abstract: Large language models are increasingly integrated into decision-making in areas such as healthcare, law, finance...
arXiv:2604.14886v1 Announce Type: new Abstract: In data-sensitive domains such as healthcare, cross-silo federated learning (CFL) allows organizations to collab...
arXiv:2604.14889v1 Announce Type: new Abstract: While Chain-of-thought (CoT) reasoning enables LLMs to solve challenging reasoning problems, as KV cache grows l...
arXiv:2604.14896v1 Announce Type: new Abstract: We present an initial investigation into Agentic Retrieval-Augmented Generation (RAG) for Ukrainian, conducted w...
arXiv:2604.14898v1 Announce Type: new Abstract: Large language models have advanced rapidly, from pattern recognition to emerging forms of reasoning, yet they r...
arXiv:2604.14902v1 Announce Type: new Abstract: Intelligent embodied agents should not simply follow instructions, as real-world environments often involve unex...
arXiv:2604.14920v1 Announce Type: new Abstract: Achieving seamless, human-like interaction remains a key challenge for full-duplex spoken dialogue models (SDMs)...
arXiv:2604.14932v1 Announce Type: new Abstract: End-to-end spoken dialogue models have garnered significant attention because they offer a higher potential ceil...
arXiv:2604.14969v1 Announce Type: new Abstract: Frontier model developers aim to train models continually to possess emergent, diverse capabilities.
arXiv:2604.14980v1 Announce Type: new Abstract: Building on recent advances in AI, hybrid decision making (HDM) holds the promise of improving human decision qu...
arXiv:2604.14987v1 Announce Type: new Abstract: Covert channels (CCs) in wireless chips pose a serious security threat, as they enable the exfiltration of sensi...
arXiv:2604.14989v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have sparked growing interest in automatic RTL optimization for...
arXiv:2604.14990v1 Announce Type: new Abstract: Artificial General Intelligence (AGI) is increasingly being discussed not only as a tool, but also as a potentia...
arXiv:2604.14991v1 Announce Type: new Abstract: As power systems transition toward renewable-rich and inverter-dominated operations, accurate time-domain dynami...
arXiv:2604.15001v1 Announce Type: new Abstract: LLM-based RTL code generation methods increasingly target both functional correctness and PPA quality, yet exist...
arXiv:2604.15009v1 Announce Type: new Abstract: Flow matching retains the generation quality of diffusion models while enabling substantially faster inference,...
arXiv:2604.15034v1 Announce Type: new Abstract: Recent advances in LLM based agent systems have shown promise in tackling complex, long horizon tasks.
arXiv:2604.15037v1 Announce Type: new Abstract: Recent advancements in LLM agents are gradually shifting from reactive, text-based paradigms toward proactive, m...
arXiv:2604.15078v1 Announce Type: new Abstract: Rapid advances in Generative AI are giving rise to increasingly sophisticated Multi-Agent AI (MAAI) systems.
arXiv:2604.15093v1 Announce Type: new Abstract: Mobile agents powered by vision-language models have demonstrated impressive capabilities in automating mobile t...
arXiv:2604.15113v1 Announce Type: new Abstract: Vector Symbolic Architectures (VSAs) provide a well-defined algebraic framework for compositional representation...
arXiv:2604.15121v1 Announce Type: new Abstract: Sequential associative memories (SAMs) are difficult to build and maintain in real-world streaming environments,...
arXiv:2604.15145v1 Announce Type: new Abstract: The rigorous evaluation of the novelty of a scientific paper is, even for human scientists, a challenging task.
arXiv:2604.15148v1 Announce Type: new Abstract: Reinforcement learning has emerged as an effective paradigm for training large language models to perform search...
arXiv:2604.15184v1 Announce Type: new Abstract: In the past year, researchers have started to create agentic systems that can design real-world CAD-style object...
arXiv:2604.15190v1 Announce Type: new Abstract: Simulating group-level user behavior enables scalable counterfactual evaluation of merchant strategies without c...
arXiv:2604.15210v1 Announce Type: new Abstract: Humor is one of the few cognitive tasks where getting the reasoning right matters as much as getting the answer...
arXiv:2604.15224v1 Announce Type: new Abstract: The $\textit{LLM-as-a-judge}$ paradigm has become the operational backbone of automated AI evaluation pipelines,...
arXiv:2604.15231v1 Announce Type: new Abstract: Vision-language models (VLM) have markedly advanced AI-driven interpretation and reporting of complex medical im...
arXiv:2604.15233v1 Announce Type: new Abstract: NL2SQL systems aim to address the growing need for natural language interaction with data.
arXiv:2604.15294v1 Announce Type: new Abstract: Over the past year, spatial intelligence has drawn increasing attention.
arXiv:2604.15302v1 Announce Type: new Abstract: LLM-as-judge frameworks are increasingly used for automatic NLG evaluation, yet their per-instance reliability r...
arXiv:2604.15306v1 Announce Type: new Abstract: Whether language models can systematically generalize remains actively debated.
arXiv:2604.14152v1 Announce Type: cross Abstract: Ambient AI "scribe" systems promise to reduce clinical documentation burden, but automatic speech recognition...
arXiv:2604.14154v1 Announce Type: cross Abstract: The rapid aging of global populations has created an urgent need for intelligent healthcare monitoring systems...
arXiv:2604.14158v1 Announce Type: cross Abstract: Current evaluations of long-term memory in LLMs are fundamentally static.
arXiv:2604.14159v1 Announce Type: cross Abstract: Mobile input method editors (IMEs) are the primary interface for text input, yet they remain constrained to ma...
arXiv:2604.14161v1 Announce Type: cross Abstract: Reliable evaluation is essential in machine learning research, yet methodological flaws-particularly data leak...
arXiv:2604.14163v1 Announce Type: cross Abstract: Maritime distress communications transmitted over very high frequency (VHF) radio are safety-critical voice me...
arXiv:2604.14167v1 Announce Type: cross Abstract: Rhetoric recognition is a critical component in automated essay scoring.
arXiv:2604.14168v1 Announce Type: cross Abstract: We introduce SAGE Celer 2.6, the latest in our line of general-purpose Celer models from SAGEA. Celer 2.
arXiv:2604.14170v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in external knowledge but often suff...
arXiv:2604.14171v1 Announce Type: cross Abstract: Romanized Nepali, the Nepali language written in the Latin alphabet, is the dominant medium for informal digit...
arXiv:2604.14172v1 Announce Type: cross Abstract: Large Language Models (LLMs) are essential for analyzing and addressing vulnerabilities in cybersecurity.
arXiv:2604.14175v1 Announce Type: cross Abstract: We present a unified system addressing both Subtask 3 (answer generation) and Subtask 4 (evidence sentence ali...
arXiv:2604.14176v1 Announce Type: cross Abstract: Generalized Category Discovery (GCD) leverages labeled data to categorize unlabeled samples from known or unkn...
arXiv:2604.14177v1 Announce Type: cross Abstract: Grammatical error correction (GEC) and explanation (GEE) have made rapid progress, but real teaching scenarios...
arXiv:2604.14179v1 Announce Type: cross Abstract: Rare diseases affect over 300 million people worldwide and are characterized by complex care pathways, limited...
arXiv:2604.14180v1 Announce Type: cross Abstract: We train a 318M-parameter Transformer language model from scratch on a curated corpus of 1.
arXiv:2604.14184v1 Announce Type: cross Abstract: Buildings and data centers (DCs) are energy-intensive sectors, playing a critical role to achieve the low-carb...
arXiv:2604.14186v1 Announce Type: cross Abstract: Large self-supervised speech (SSL) models achieve strong downstream performance, but their size limits deploym...
arXiv:2604.14188v1 Announce Type: cross Abstract: Large language models have demonstrated impressive performance across many domains of mathematics and physics.
arXiv:2604.14197v1 Announce Type: cross Abstract: Large language model (LLM) performance depends heavily on prompt design, yet prompt construction is often desc...
arXiv:2604.14198v1 Announce Type: cross Abstract: Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization...
arXiv:2604.14199v1 Announce Type: cross Abstract: Predicting real-world events from live market signals demands systems that fuse qualitative news with quantita...
arXiv:2604.14200v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) are vulnerable to elaborately designed adversarial noise, although they have achie...
arXiv:2604.14202v1 Announce Type: cross Abstract: Electroencephalography (EEG) has become one of the key modalities underpinning brain-computer interfaces (BCIs...
arXiv:2604.14204v1 Announce Type: cross Abstract: Multimodal emotion recognition in conversations aims to infer utterance-level emotions by jointly modeling tex...
arXiv:2604.14209v1 Announce Type: cross Abstract: As deep neural networks are deployed in safety-critical domains such as autonomous driving and medical diagnos...
arXiv:2604.14211v1 Announce Type: cross Abstract: This thesis is an exposition of Ollivier-Ricci Curvature of metric spaces as introduced by Yann Ollivier, whic...
arXiv:2604.14214v1 Announce Type: cross Abstract: Large Language Models utilizing reasoning techniques improve task performance but incur significant latency an...
arXiv:2604.14215v1 Announce Type: cross Abstract: To address the unsustainable rise in public health expenditures, the Hong Kong SAR Government is shifting its...
arXiv:2604.14216v1 Announce Type: cross Abstract: Predicting post-surgical seizure outcomes in pharmacoresistant epilepsy is a clinical challenge.
arXiv:2604.14218v1 Announce Type: cross Abstract: Hate speech detection in Devanagari-scripted social media memes presents compounded challenges: multimodal con...
arXiv:2604.14220v1 Announce Type: cross Abstract: This research paper addresses the limitations of semantic search in complex enterprise document ecosystems.
arXiv:2604.14222v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become the standard paradigm for grounding Large Language Model outpu...
arXiv:2604.14223v1 Announce Type: cross Abstract: Traditional conversational travel recommender systems primarily optimize for user relevance and convenience, o...
arXiv:2604.14227v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is a key approach to mitigating the temporal staleness of large language...
arXiv:2604.14228v1 Announce Type: cross Abstract: Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on b...
arXiv:2604.14229v1 Announce Type: cross Abstract: Synthetic Aperture Radar (SAR) data is inherently complex-valued, while quantum machine learning (QML) models...
arXiv:2604.14231v1 Announce Type: cross Abstract: Financial crime costs U.S. institutions over $32 billion each year.
arXiv:2604.14232v1 Announce Type: cross Abstract: The Spatial-Temporal Graph Attention Network (ST-GAT) framework was created to serve as an explainable GNN-bas...
arXiv:2604.14235v1 Announce Type: cross Abstract: Fraud detection on graph data can be viewed as a demanding task that requires distinguishing between different...
arXiv:2604.14243v1 Announce Type: cross Abstract: Real-world decision-making systems operate in environments where state transitions depend not only on the agen...
arXiv:2604.14246v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) models have achieved remarkable scalability, yet they remain vulnerable to hal...
arXiv:2604.14256v1 Announce Type: cross Abstract: Modern information access ecosystems consist of mixtures of systems, such as retrieval systems and large langu...
arXiv:2604.14261v1 Announce Type: cross Abstract: The rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs)...
arXiv:2604.14262v1 Announce Type: cross Abstract: GUI grounding models report over 85% accuracy on standard benchmarks, yet drop 27-56 percentage points when in...
arXiv:2604.14265v1 Announce Type: cross Abstract: We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distributio...
arXiv:2604.14267v1 Announce Type: cross Abstract: Search agents extend Large Language Models (LLMs) beyond static parametric knowledge by enabling access to up-...
arXiv:2604.14287v1 Announce Type: cross Abstract: Tensor networks were developed in the context of many-body physics as compressed representations of multiparti...
arXiv:2604.14306v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have demonstrated high proficiency on English-centric medical examinations,...
arXiv:2604.14309v1 Announce Type: cross Abstract: To address high data traffic demands of sixth-generation (6G) networks, this paper proposes a novel architectu...
arXiv:2604.14314v1 Announce Type: cross Abstract: This manuscript introduces DharmaOCR Full and Lite, a pair of specialized small language models (SSLMs) for st...
arXiv:2604.14317v1 Announce Type: cross Abstract: Agentic systems built on large language models (LLMs) are increasingly being used for complex security tasks,...
arXiv:2604.14325v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong performance and have revolutionized NLP, but their lack of explain...
arXiv:2604.14332v1 Announce Type: cross Abstract: Diffusion-model inference and overdamped Langevin dynamics are formally identical.
arXiv:2604.14334v1 Announce Type: cross Abstract: Gradient saliency from deep sequence models surfaces candidate biomarkers efficiently, but the resulting gene...
arXiv:2604.14345v1 Announce Type: cross Abstract: As search depth increases in autonomous reasoning and embodied planning, the candidate action space expands ex...
arXiv:2604.14356v1 Announce Type: cross Abstract: Women with polycystic ovary syndrome (PCOS) face substantially elevated risks of body image distress, disorder...
arXiv:2604.14362v1 Announce Type: cross Abstract: Large language models still struggle with reliable long-term conversational memory: simply enlarging context w...
arXiv:2604.14363v1 Announce Type: cross Abstract: Multimodal language models systematically underperform on visual perception tasks, yet the structure underlyin...
arXiv:2604.14373v1 Announce Type: cross Abstract: Rural environmental risks are shaped by place-based conditions (e.g.
arXiv:2604.14375v1 Announce Type: cross Abstract: Catastrophic forgetting remains a primary hurdle in sequential task learning for artificial neural networks.
arXiv:2604.14379v1 Announce Type: cross Abstract: Reinforcement learning (RL) has emerged as a powerful tool for aligning diffusion models with human preference...
arXiv:2604.14386v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly deployed in multi-agent systems requiring strategic coordin...
arXiv:2604.14389v1 Announce Type: cross Abstract: Automated fact-checking in dialogue involves multi-turn conversations where colloquial language is frequent ye...
arXiv:2604.14397v1 Announce Type: cross Abstract: We study the task of automatically expanding WordNet-style lexical resources to new languages through sense ge...
arXiv:2604.14399v1 Announce Type: cross Abstract: Autonomous on-orbit servicing demands embodied agents that perceive through visual sensors, reason about 3D sp...
arXiv:2604.14430v1 Announce Type: cross Abstract: We present Three-Phase Transformer (3PT), a residual-stream structural prior for decoder-only Transformers on...
arXiv:2604.14437v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved impressive results on public benchmarks, often leading to claims of...
arXiv:2604.14442v1 Announce Type: cross Abstract: We present an empirical study of whether hierarchically structured, shared-weight recurrence can match the rep...
arXiv:2604.14444v1 Announce Type: cross Abstract: Ensuring the reliability of machine learning-based intrusion detection systems remains a critical challenge in...
arXiv:2604.14449v1 Announce Type: cross Abstract: Recent advances in data-centric artificial intelligence highlight inherent limitations in object recognition d...
arXiv:2604.14451v1 Announce Type: cross Abstract: Weak gravitational lensing, the correlated distortion of background galaxy shapes by foreground structures, is...
arXiv:2604.14456v1 Announce Type: cross Abstract: Visualizing narratives is useful to writers to reflect on unfinished drafts and identify unintentional biases...
arXiv:2604.14472v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) are often selected by a single scalar loss even when the quantity of...
arXiv:2604.14484v1 Announce Type: cross Abstract: Behavior cloning (BC) policies on position-controlled robots inherit the closed-loop response of the underlyin...
arXiv:2604.14495v1 Announce Type: cross Abstract: Financial institutions face tension between maximizing data utility and mitigating the re-identification risks...
arXiv:2604.14501v1 Announce Type: cross Abstract: We study the expressive power and limitations of multi-layer state-space models (SSMs).
arXiv:2604.14510v1 Announce Type: cross Abstract: News recommender systems are devised to alleviate the information overload, attracting more and more researche...
arXiv:2604.14512v1 Announce Type: cross Abstract: Agent communication languages (ACLs) enable heterogeneous agents to share knowledge and coordinate across dive...
arXiv:2604.14532v1 Announce Type: cross Abstract: Accurate prediction of future risk and disease progression in sepsis is clinically important for early warning...
arXiv:2604.14550v1 Announce Type: cross Abstract: Generating synthesizable Verilog for large, hierarchical hardware designs remains a significant challenge for...
arXiv:2604.14556v1 Announce Type: cross Abstract: Video object insertion is a critical task for dynamically inserting new objects into existing environments.
arXiv:2604.14572v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds LLM responses in external evidence but treats the model as a pass...
arXiv:2604.14575v1 Announce Type: cross Abstract: Data-driven operations management often relies on parameters estimated from costly human-generated labels.
arXiv:2604.14586v1 Announce Type: cross Abstract: The rapid expansion of gaming industry requires advanced recommender systems tailored to its dynamic landscape...
arXiv:2604.14590v1 Announce Type: cross Abstract: In modern data-streaming systems, alongside traditional programs, a new type of entity has emerged that can in...
arXiv:2604.14593v1 Announce Type: cross Abstract: While Large Language Models (LLMs) demonstrate increasingly sophisticated affective capabilities, the internal...
arXiv:2604.14602v1 Announce Type: cross Abstract: Large language models (LLMs) frequently generate toxic content, posing significant risks for safe deployment.
arXiv:2604.14604v1 Announce Type: cross Abstract: Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio a...
arXiv:2604.14613v1 Announce Type: cross Abstract: Learning Path Recommendation (LPR) is critical for personalized education, yet current methods often fail to a...
arXiv:2604.14616v1 Announce Type: cross Abstract: Clinical value set authoring -- the task of identifying all codes in a standardized vocabulary that define a c...
arXiv:2604.14624v1 Announce Type: cross Abstract: Humans often specify tasks incompletely, so assistants must know when and how to ask clarifying questions.
arXiv:2604.14626v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models have become the dominant architecture for large-scale language models, yet on-...
arXiv:2604.14631v1 Announce Type: cross Abstract: Effective code generation requires both model capability and a problem representation that carefully structure...
arXiv:2604.14640v1 Announce Type: cross Abstract: The proliferation of financial misinformation poses a severe threat to market stability and investor trust, mi...
arXiv:2604.14645v1 Announce Type: cross Abstract: Convolutional neural networks (CNNs) often exhibit poor generalisation in limited training data scenarios due...
arXiv:2604.14648v1 Announce Type: cross Abstract: Video outpainting aims to expand the visible content of a video beyond the original frame boundaries while pre...
arXiv:2604.14661v1 Announce Type: cross Abstract: Edge AI model deployment is a multi-stage engineering process involving model conversion, operator compatibili...
arXiv:2604.14723v1 Announce Type: cross Abstract: Large language models are increasingly used as natural-language interfaces to enterprise software, but their d...
arXiv:2604.14726v1 Announce Type: cross Abstract: Online anomaly detection (OAD) plays a pivotal role in real-time analytics and decision-making for evolving da...
arXiv:2604.14749v1 Announce Type: cross Abstract: Large language models still struggle with faithfulness and hallucinations despite their remarkable reasoning a...
arXiv:2604.14766v1 Announce Type: cross Abstract: Preventing machine failure is inherently superior to reactive remediation, particularly for critical assets li...
arXiv:2604.14846v1 Announce Type: cross Abstract: Retail theft costs the global economy over \$100 billion annually, yet existing AI-based detection systems req...
arXiv:2604.14849v1 Announce Type: cross Abstract: Purpose: Adaptive skip modules can improve medical image segmentation, but searching for them is computational...
arXiv:2604.14856v1 Announce Type: cross Abstract: Understanding climate change requires reasoning over complex causal networks.
arXiv:2604.14862v1 Announce Type: cross Abstract: Constrained decoding has been widely adopted for structured generation with large language models (LLMs), ensu...
arXiv:2604.14866v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated significant potential in medical image analysis, yet their app...
arXiv:2604.14867v1 Announce Type: cross Abstract: Vibe coding inherently assumes iterative refinement of LLM-generated code through feedback loops.
arXiv:2604.14878v1 Announce Type: cross Abstract: Generative Retrieval (GR) offers a promising paradigm for recommendation through next-token prediction (NTP).
arXiv:2604.14879v1 Announce Type: cross Abstract: Nonlinear system identification must balance physical interpretability with model flexibility.
arXiv:2604.14885v1 Announce Type: cross Abstract: Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference l...
arXiv:2604.14888v1 Announce Type: cross Abstract: Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integr...
arXiv:2604.14892v1 Announce Type: cross Abstract: Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large la...
arXiv:2604.14895v1 Announce Type: cross Abstract: We propose a new perspective on policy optimization: rather than reweighting all samples by their importance r...
arXiv:2604.14925v1 Announce Type: cross Abstract: Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in fou...
arXiv:2604.14927v1 Announce Type: cross Abstract: Many CAD learning pipelines discretize Boundary Representations (B-Reps) into triangle meshes, discarding anal...
arXiv:2604.14951v1 Announce Type: cross Abstract: Tool learning with foundation models aims to endow AI systems with the ability to invoke external resources --...
arXiv:2604.14961v1 Announce Type: cross Abstract: Contextual bandit algorithms suffer from high regret during cold-start, when the learner has insufficient data...
arXiv:2604.14967v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) extends Large Vision-Language Models (LVLMs) with external visual knowled...
arXiv:2604.14984v1 Announce Type: cross Abstract: As companies enter the race for agentic AI adoption, fears surface around agentic autonomy and its subsequent...
arXiv:2604.15010v1 Announce Type: cross Abstract: When do transformers commit to a decision, and what prevents them from correcting it?
arXiv:2604.15022v1 Announce Type: cross Abstract: Cost-aware routing dynamically dispatches user queries to models of varying capability to balance performance...
arXiv:2604.15038v1 Announce Type: cross Abstract: The evaluation of fairness in machine learning systems has become a central concern in high-stakes application...
arXiv:2604.15044v1 Announce Type: cross Abstract: The increasing integration of artificial intelligence (AI) in everyday life brings with it new challenges and...
arXiv:2604.15063v1 Announce Type: cross Abstract: Gradient inversion attacks threaten client privacy in federated learning by reconstructing training samples fr...
arXiv:2604.15076v1 Announce Type: cross Abstract: To navigate a space, the brain makes an internal representation of the environment using different cells such...
arXiv:2604.15082v1 Announce Type: cross Abstract: This paper introduces the first \emph{self-evolving} logic synthesis framework, which leverages Large Language...
arXiv:2604.15109v1 Announce Type: cross Abstract: Despite the rapid advancement of Large Language Models (LLMs), uncertainty quantification in LLM generation is...
arXiv:2604.15114v1 Announce Type: cross Abstract: We propose a novel amortized optimization method for predicting optimal transport (OT) plans across multiple p...
arXiv:2604.15143v1 Announce Type: cross Abstract: This work simulates the developmental process of cortical neurogenesis, initiating from a single stem cell and...
arXiv:2604.15149v1 Announce Type: cross Abstract: As reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for scaling reasonin...
arXiv:2604.15153v1 Announce Type: cross Abstract: Large Language Models (LLMs) incur significant computational and memory costs when processing long prompts, as...
arXiv:2604.15166v1 Announce Type: cross Abstract: Machine unlearning aims to remove targeted knowledge from a trained model without the cost of retraining from...
arXiv:2604.15174v1 Announce Type: cross Abstract: Despite recent advances in state space models (SSMs) such as Mamba across various sequence domains, research o...
arXiv:2604.15186v1 Announce Type: cross Abstract: Agentic workflows carry out complex tasks by orchestrating multiple large language models (LLMs) and tools.
arXiv:2604.15188v1 Announce Type: cross Abstract: Visual token pruning methods effectively mitigate the quadratic computational growth caused by processing high...
arXiv:2604.15202v1 Announce Type: cross Abstract: Coverage path planning on irregular hexagonal grids is relevant to maritime surveillance, search and rescue an...
arXiv:2604.15222v1 Announce Type: cross Abstract: Artificial Intelligence is increasingly introduced into systems engineering activities, particularly within re...
arXiv:2604.15236v1 Announce Type: cross Abstract: This paper advances a methodological proposal for safety research in agentic AI.
arXiv:2604.15259v1 Announce Type: cross Abstract: Looped transformers promise test-time compute scaling by spending more iterations on harder problems, but it r...
arXiv:2604.15267v1 Announce Type: cross Abstract: It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents,...
arXiv:2604.15271v1 Announce Type: cross Abstract: Reliable uncertainty estimation is critical for medical image segmentation, where automated contours feed down...
arXiv:2604.15272v1 Announce Type: cross Abstract: This paper presents Prism, the first symbolic superoptimizer for tensor programs.
arXiv:2604.15280v1 Announce Type: cross Abstract: Understanding emotions is a fundamental ability for intelligent systems to be able to interact with humans.
arXiv:2604.15291v1 Announce Type: cross Abstract: The reliability of a machine vision system for autonomous driving depends heavily on its training data distrib...
arXiv:2604.15309v1 Announce Type: cross Abstract: The rapid progress of Artificial Intelligence Generated Content (AIGC) tools enables images, videos, and visua...
arXiv:2309.11452v3 Announce Type: replace Abstract: The Boolean Satisfiability problem (SAT), as the prototypical $\mathsf{NP}$-complete problem, is crucial in...
arXiv:2402.08780v2 Announce Type: replace Abstract: This research project presents the implementation of a Deep Q-Learning Network (DQN) for a self-driving car...
arXiv:2505.09755v3 Announce Type: replace Abstract: Deep learning models have shown promise in lung pathology detection from chest X-rays, but widespread clinic...
arXiv:2505.20214v2 Announce Type: replace Abstract: Reasoning models have attracted increasing attention for their ability to tackle complex tasks, embodying th...
arXiv:2506.19807v4 Announce Type: replace Abstract: Large Language Models (LLMs), particularly slow-thinking models, often exhibit severe hallucination, outputt...
arXiv:2507.15351v3 Announce Type: replace Abstract: Order dispatch is a critical task in ride-sharing systems with Autonomous Vehicles (AVs), directly influenci...
arXiv:2508.01330v3 Announce Type: replace Abstract: Despite significant advances in LLM-driven GUI agents, the field remains constrained by the challenge of rec...
arXiv:2508.03341v4 Announce Type: replace Abstract: Memory systems for LLM agents struggle to determine what information deserves retention.
arXiv:2510.03851v2 Announce Type: replace Abstract: Designing system algorithms remains challenging, where the discontinuous nature of the solution space often...
arXiv:2510.04116v4 Announce Type: replace Abstract: Meta reasoning behaviors work as a skeleton to guide large language model (LLM) reasoning, thus help to impr...
arXiv:2510.10649v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has shown significant promise for enhancing the reason...
arXiv:2510.14665v2 Announce Type: replace Abstract: As large language models (LLMs) become integrated into everyday and high-stakes decision-making, they inheri...
arXiv:2510.24284v3 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly rely on external tools to perform complex, realistic tasks, yet th...
arXiv:2511.09363v2 Announce Type: replace Abstract: Safety verification of dynamical systems via barrier certificates is essential for ensuring correctness in a...
arXiv:2511.15825v2 Announce Type: replace Abstract: IMACT-CXR is an interactive multi-agent conversational tutor that helps trainees interpret chest X-rays by u...
arXiv:2511.20892v3 Announce Type: replace Abstract: Large language models (LLMs) often produce incorrect or outdated content after being employed.
arXiv:2512.03048v4 Announce Type: replace Abstract: Static content-based AI value alignment is insufficient for robust alignment under capability scaling, distr...
arXiv:2512.13168v5 Announce Type: replace Abstract: We introduce FinWorkBench (a.k.a.
arXiv:2601.03236v2 Announce Type: replace Abstract: Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context...
arXiv:2602.01869v2 Announce Type: replace Abstract: LLM-driven agents demonstrate strong performance in sequential decision-making but often rely on on-the-fly...
arXiv:2602.12389v3 Announce Type: replace Abstract: Temporal knowledge graph (TKG) forecasting requires predicting future facts by jointly modeling structural d...
arXiv:2602.22842v2 Announce Type: replace Abstract: Can artificial intelligence truly contribute to creative mathematical research, or does it merely automate r...
arXiv:2603.02196v2 Announce Type: replace Abstract: An agent must try new behaviors to explore and improve.
arXiv:2603.03686v3 Announce Type: replace Abstract: Automated design of chemical formulations is a cornerstone of materials science, yet it requires navigating...
arXiv:2603.18294v2 Announce Type: replace Abstract: Background: Clinical trials rely on transparent inclusion criteria to ensure generalizability.
arXiv:2603.29693v2 Announce Type: replace Abstract: A robust decision-making process must take into account uncertainty, especially when the choice involves inh...
arXiv:2604.02585v2 Announce Type: replace Abstract: LLMs are increasingly used for high-stakes decision-making, yet their sensitivity to spurious contextual inf...
arXiv:2604.03588v2 Announce Type: replace Abstract: AI agents operating over extended time horizons accumulate experiences that serve multiple concurrent goals,...
arXiv:2604.05407v3 Announce Type: replace Abstract: LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matchin...
arXiv:2604.10410v2 Announce Type: replace Abstract: Interpreting chest X-rays is inherently challenging due to the overlap between anatomical structures and the...
arXiv:2604.11077v2 Announce Type: replace Abstract: Customer service chatbots are increasingly expected to serve not merely as reactive support tools for users,...
arXiv:2604.11623v3 Announce Type: replace Abstract: We introduce Context Kubernetes, an architecture for orchestrating enterprise knowledge in agentic AI system...
arXiv:2604.12019v2 Announce Type: replace Abstract: Although artificial intelligence (AI) agents are increasingly proposed to support potentially longitudinal h...
arXiv:2604.12210v2 Announce Type: replace Abstract: Simulating Standardized Patients with cognitive impairment offers a scalable and ethical solution for clinic...
arXiv:2604.12390v2 Announce Type: replace Abstract: This paper addresses two limitations of large language models (LLMs) in solving complex problems: (1) their...
arXiv:2604.12667v2 Announce Type: replace Abstract: Human-robot collaborative manufacturing, a core aspect of Industry 5.
arXiv:2604.12669v2 Announce Type: replace Abstract: In advanced manufacturing systems, humans and robots collaborate to conduct the production process.
arXiv:2604.12955v2 Announce Type: replace Abstract: There is growing interest in leveraging large language models (LLMs) for text-to-model translation and optim...
arXiv:2311.01956v2 Announce Type: replace-cross Abstract: Web3 systems expose a fundamentally different security landscape from centralized platforms, character...
arXiv:2311.04799v2 Announce Type: replace-cross Abstract: Pretraining language models is still a challenge for many researchers due to its substantial computati...
arXiv:2403.10559v3 Announce Type: replace-cross Abstract: This report investigates the history and impact of Generative Models and Connected and Automated Vehic...
arXiv:2408.14728v2 Announce Type: replace-cross Abstract: Adversarial training has proven effective in improving the robustness of deep neural networks against...
arXiv:2410.01540v4 Announce Type: replace-cross Abstract: Classical diffusion models typically rely on isotropic Gaussian noise, treating all regions uniformly...
arXiv:2410.17448v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are transformer-based machine learning models that have shown remarkable...
arXiv:2502.04689v4 Announce Type: replace-cross Abstract: Intent, a critical cognitive notion and mental state, is ubiquitous in human communication and problem...
arXiv:2502.07408v2 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) can be catastrophically disrupted by flipping only a handful of parameter...
arXiv:2502.12222v2 Announce Type: replace-cross Abstract: The eXplainable Artificial Intelligence (XAI) research predominantly concentrates to provide explainat...
arXiv:2505.14838v2 Announce Type: replace-cross Abstract: Understanding the impact of scientific publications is crucial for identifying breakthroughs and guidi...
arXiv:2506.11251v2 Announce Type: replace-cross Abstract: A suitable scalar metric can help measure multi-calibration, defined as follows.
arXiv:2506.13763v2 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable success in generative modeling.
arXiv:2506.23334v3 Announce Type: replace-cross Abstract: Federated learning enables collaborative training of deep learning models across institutions without...
arXiv:2507.02935v2 Announce Type: replace-cross Abstract: Successful human-agent teaming relies on an agent being able to understand instructions given by a (hu...
arXiv:2507.15066v5 Announce Type: replace-cross Abstract: Time series anomaly detection (TSAD) has traditionally focused on binary classification and often lack...
arXiv:2507.23121v2 Announce Type: replace-cross Abstract: In this work, we study a critical research problem regarding the trustworthiness of large language mod...
arXiv:2508.05015v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforceme...
arXiv:2508.20705v3 Announce Type: replace-cross Abstract: Recent advances in self-supervised learning for EEG representation have largely relied on masked recon...
arXiv:2509.02571v2 Announce Type: replace-cross Abstract: This paper investigates continuous representations of steering vectors over frequency and microphone/s...
arXiv:2509.03472v2 Announce Type: replace-cross Abstract: Differentially-Private SGD (DP-SGD) and its adaptive variant DP-Adam are powerful techniques to protec...
arXiv:2509.14003v2 Announce Type: replace-cross Abstract: Diffusion models have shown remarkable progress in text-to-audio generation.
arXiv:2509.14255v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models improve efficiency through sparse activation, but their learned gating...
arXiv:2509.20869v2 Announce Type: replace-cross Abstract: Delays frequently occur in real-world environments, yet standard reinforcement learning (RL) algorithm...
arXiv:2509.22378v2 Announce Type: replace-cross Abstract: Recently, Image-to-Music (I2M) generation has garnered significant attention, with potential applicati...
arXiv:2509.23468v3 Announce Type: replace-cross Abstract: Effectively integrating diverse sensory modalities is crucial for robotic manipulation.
arXiv:2509.26007v2 Announce Type: replace-cross Abstract: Research on audio generation has progressively developed along both waveform-based and spectrogram-bas...
arXiv:2510.01433v2 Announce Type: replace-cross Abstract: Vision-based robot learning often relies on dense image or point-cloud inputs, which are computational...
arXiv:2510.06708v2 Announce Type: replace-cross Abstract: Conducting systematic reviews is laborious.
arXiv:2510.08483v2 Announce Type: replace-cross Abstract: Parallel scaling has emerged as a powerful paradigm to enhance reasoning capabilities in large languag...
arXiv:2510.13829v3 Announce Type: replace-cross Abstract: As large language models (LLMs) continue to advance rapidly, reliable governance tools have become cri...
arXiv:2510.14509v4 Announce Type: replace-cross Abstract: The rapid advancement in large language models (LLMs) has demonstrated significant potential in End-to...
arXiv:2510.15946v3 Announce Type: replace-cross Abstract: Internet memes have emerged as a popular multimodal medium, yet they are increasingly weaponized to co...
arXiv:2510.17932v3 Announce Type: replace-cross Abstract: We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation ca...
arXiv:2511.01838v2 Announce Type: replace-cross Abstract: Vector symbolic architectures (VSAs) are a family of information representation techniques which enabl...
arXiv:2511.09149v4 Announce Type: replace-cross Abstract: While natural language is the de facto communication medium for LLM-based agents, it presents a fundam...
arXiv:2511.14178v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have demonstrated significant potential in real-world robotic mani...
arXiv:2511.22521v2 Announce Type: replace-cross Abstract: Document visual question answering requires models not only to answer questions correctly, but also to...
arXiv:2512.05024v3 Announce Type: replace-cross Abstract: As generative AI models are increasingly used to simulate real-world systems, quantifying the ``sim-to...
arXiv:2512.10159v2 Announce Type: replace-cross Abstract: LLMs have demonstrated strong performance in data-rich domains such as programming, yet their reliabil...
arXiv:2512.15925v2 Announce Type: replace-cross Abstract: Reading stories evokes rich interpretive, affective, and evaluative responses, such as inferences abou...
arXiv:2512.17091v2 Announce Type: replace-cross Abstract: We propose a new approach for solving planning problems with a hierarchical structure, fusing reinforc...
arXiv:2512.24120v2 Announce Type: replace-cross Abstract: Automated neural network architecture design remains a significant challenge in computer vision.
arXiv:2601.07449v2 Announce Type: replace-cross Abstract: Review ranking is pivotal in e-commerce for prioritizing diagnostic and authentic feedback from the de...
arXiv:2601.07667v2 Announce Type: replace-cross Abstract: Due to the prevalence of large language models (LLMs), key-value (KV) cache reduction for LLM inferenc...
arXiv:2601.08310v2 Announce Type: replace-cross Abstract: Recent Large Reasoning Models (LRMs) achieve strong performance by leveraging long-form Chain-of-Thoug...
arXiv:2601.10120v2 Announce Type: replace-cross Abstract: Optimizing communication topology in LLM-based multi-agent system is critical for enabling collective...
arXiv:2601.14053v2 Announce Type: replace-cross Abstract: The field of artificial intelligence has undergone a revolution from foundational Transformer architec...
arXiv:2601.14724v3 Announce Type: replace-cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated significant improvem...
arXiv:2601.15488v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit social biases, which can lead to harmful stereotypes and unfair o...
arXiv:2601.18675v2 Announce Type: replace-cross Abstract: We investigate whether temporal embedding models trained on longitudinal electronic health records can...
arXiv:2601.20868v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have advanced the field of Combinatorial Optimization through automated h...
arXiv:2602.03295v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) have demonstrated remarkable capabiliti...
arXiv:2602.04930v2 Announce Type: replace-cross Abstract: Future AI deployments will likely be monitored for malicious behaviour.
arXiv:2602.07069v2 Announce Type: replace-cross Abstract: Powered by multimodal text-to-image priors, diffusion-based super-resolution excels at synthesizing in...
arXiv:2603.03897v3 Announce Type: replace-cross Abstract: Foundation models have demonstrated impressive capabilities across diverse domains, while imitation le...
arXiv:2603.09643v5 Announce Type: replace-cross Abstract: Current evaluation frameworks and benchmarks for LLM powered agents focus on text chat driven agents,...
arXiv:2603.12277v4 Announce Type: replace-cross Abstract: Language models remain vulnerable to prompt injection attacks despite extensive safety training.
arXiv:2603.13683v2 Announce Type: replace-cross Abstract: Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often...
arXiv:2603.18373v2 Announce Type: replace-cross Abstract: When VLMs answer correctly, do they genuinely rely on visual information or exploit language shortcuts...
arXiv:2603.23315v4 Announce Type: replace-cross Abstract: When providers update AI companions, users report grief, betrayal, and loss.
arXiv:2603.24448v2 Announce Type: replace-cross Abstract: Current clinical decision support systems (CDSSs) typically base their predictions on correlation, not...
arXiv:2603.24470v2 Announce Type: replace-cross Abstract: Every year, 10 million pets enter shelters, separated from their families.
arXiv:2604.03307v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success, yet they remain prone to pe...
arXiv:2604.05242v2 Announce Type: replace-cross Abstract: Multi-bit watermarking has emerged as a promising solution for embedding imperceptible binary messages...
arXiv:2604.05418v3 Announce Type: replace-cross Abstract: Scaling multimodal large language models (MLLMs) to long videos is constrained by limited context wind...
arXiv:2604.06296v2 Announce Type: replace-cross Abstract: AI agents are increasingly deployed in real-world applications, including systems such as Manus, OpenC...
arXiv:2604.07349v5 Announce Type: replace-cross Abstract: Any rigorously specified problem determines an admissible-output relation $R$, and exact correctness d...
arXiv:2604.07941v2 Announce Type: replace-cross Abstract: Post-training has become central to turning pretrained large language models (LLMs) into aligned, capa...
arXiv:2604.09665v2 Announce Type: replace-cross Abstract: While the wide adoption of refusal training in large language models (LLMs) has showcased improvements...
arXiv:2604.09734v2 Announce Type: replace-cross Abstract: We study how far structured architectural bias can compensate for the absence of end-to-end gradient-b...
arXiv:2604.10427v2 Announce Type: replace-cross Abstract: We develop a queueing-theoretic framework to model the temporal evolution of cyber-attack surfaces, wh...
arXiv:2604.10681v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs), despite their impressive capabilities across domains, have been shown to...
arXiv:2604.10966v2 Announce Type: replace-cross Abstract: We present a discriminative multimodal reward model that scores all candidate responses in a single fo...
arXiv:2604.11026v3 Announce Type: replace-cross Abstract: We study the problem of characterizing the stability of Kullback-Leibler (KL) divergence under Gaussia...
arXiv:2604.11427v3 Announce Type: replace-cross Abstract: Developing non-collaborative dialogue agents traditionally requires the manual, unscalable codificatio...
arXiv:2604.11502v2 Announce Type: replace-cross Abstract: Contextual causal reasoning is a critical yet challenging capability for Large Language Models (LLMs).
arXiv:2604.11508v2 Announce Type: replace-cross Abstract: Fine-tuning pretrained image classifiers is standard practice, yet which individual samples are forgot...
arXiv:2604.11665v3 Announce Type: replace-cross Abstract: This paper reports an unexpected finding: in a deterministic hyperdimensional computing (HDC) architec...
arXiv:2604.13466v2 Announce Type: replace-cross Abstract: The Claude Mythos Preview system card deploys emotion vectors, sparse autoencoder (SAE) features, and...
arXiv:2604.14137v2 Announce Type: replace-cross Abstract: Evaluating LLMs is challenging, as benchmark scores often fail to capture models' real-world usefulnes...
arXiv:2604.14206v1 Announce Type: new Abstract: This paper proposes a machine learning assisted portfolio optimization framework designed for low data environme...
arXiv:2604.14237v1 Announce Type: new Abstract: Transistor topology optimization is a critical step in standard cell design, directly dictating diffusion sharin...
arXiv:2604.14249v1 Announce Type: new Abstract: We introduce Metric-Aware Principal Component Analysis (MAPCA), a unified framework for scale-invariant represen...
arXiv:2604.14251v1 Announce Type: new Abstract: Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every...
arXiv:2604.14331v1 Announce Type: new Abstract: Applying kernel methods to matchings is challenging due to their discrete, non-Euclidean nature.
arXiv:2604.14333v1 Announce Type: new Abstract: Key Opinion Leader (KOL) discourse on social media is widely consumed as investment guidance, yet turning it int...
arXiv:2604.14338v1 Announce Type: new Abstract: We introduce path-sampled integrated gradients (PS-IG), a framework that generalizes feature attribution by comp...
arXiv:2604.14424v1 Announce Type: new Abstract: Most practical engineering design problems involve nonlinear spatio-temporal dynamical systems.
arXiv:2604.14450v1 Announce Type: new Abstract: Quick and accurate emergency handling in Disaster Decision Support Systems (DDSS) is often hampered by network l...
arXiv:2604.14474v1 Announce Type: new Abstract: Traditional esports scouting workflows rely heavily on manual video review and aggregate performance metrics, wh...
arXiv:2604.14487v1 Announce Type: new Abstract: Quantization is a natural complement to the sparse, event-driven computation of Spiking Neural Networks, reducin...
arXiv:2604.14519v1 Announce Type: new Abstract: Catastrophic forgetting remains a fundamental challenge in continual learning, in which models often forget prev...
arXiv:2604.14534v1 Announce Type: new Abstract: Purpose. Athlete monitoring is constrained by small cohorts, heterogeneous biomarker scales, limited feasibility...
arXiv:2604.14547v1 Announce Type: new Abstract: Objective: Post-traumatic epilepsy (PTE) is a debilitating neurological disorder that develops after traumatic b...
arXiv:2604.14562v1 Announce Type: new Abstract: Accurate thermal modeling in metal additive manufacturing (AM) is essential for understanding the process-struct...
arXiv:2604.14566v1 Announce Type: new Abstract: Accurate temperature estimation of pouch cells with indirect liquid cooling is essential for optimizing battery...
arXiv:2604.14583v1 Announce Type: new Abstract: Decentralized Finance (DeFi) lending protocols like Aave v3 rely on over-collateralization to secure loans, yet...
arXiv:2604.14587v1 Announce Type: new Abstract: Lion optimizer is a popular learning-based optimization algorithm in machine learning, which shows impressive pe...
arXiv:2604.14612v1 Announce Type: new Abstract: Self-speculative decoding is an inference technique for large language models designed to speed up generation wi...
arXiv:2604.14669v1 Announce Type: new Abstract: Zeroth-order (ZO) methods are widely used when gradients are unavailable or prohibitively expensive, including b...
arXiv:2604.14698v1 Announce Type: new Abstract: Diffusion models have recently emerged as expressive policy representations for online reinforcement learning (R...
arXiv:2604.14702v1 Announce Type: new Abstract: Multiplicative gating is widely used in neural architectures and has recently been applied to attention layers t...
arXiv:2604.14722v1 Announce Type: new Abstract: Transformers commonly exhibit an attention sink: disproportionately high attention to the first position.
arXiv:2604.14727v1 Announce Type: new Abstract: To quantify the geometric expressivity of transformers, we introduce a tropical geometry framework to characteri...
arXiv:2604.14739v1 Announce Type: new Abstract: Large-scale renewable energy deployment introduces pronounced volatility into the electricity system, turning gr...
arXiv:2604.14765v1 Announce Type: new Abstract: We present a geometric framework for Reinforcement Learning (RL) that views policies as maps into the Wasserstei...
arXiv:2604.14769v1 Announce Type: new Abstract: The pre-training and fine-tuning paradigm has become the dominant approach for model adaptation.
arXiv:2604.14811v1 Announce Type: new Abstract: Ad hoc wireless networks exhibit complex, innate and coupled dynamics: node mobility, energy depletion and topol...
arXiv:2604.14853v1 Announce Type: new Abstract: Test-time compute scaling, the practice of spending extra computation during inference via repeated sampling, se...
arXiv:2604.14870v1 Announce Type: new Abstract: Local loss-landscape stabilization under sample growth is typically measured either pointwise or through isotrop...
arXiv:2604.14877v1 Announce Type: new Abstract: Does reinforcement learning genuinely expand what LLM agents can do, or merely make them more reliable?
arXiv:2604.14880v1 Announce Type: new Abstract: Recent advances in Deep Learning (DL) have boosted data-driven System Identification (SysID), but reliable use r...
arXiv:2604.14883v1 Announce Type: new Abstract: Recent advances in Deep Learning (DL) have strengthened data-driven System Identification (SysID), with Neural a...
arXiv:2604.14908v1 Announce Type: new Abstract: We study downlink beam and rate adaptation in a multi-user mmWave MISO system where multiple base stations (BSs)...
arXiv:2604.14922v1 Announce Type: new Abstract: Reinforcement Learning (RL) has emerged as a critical driver for enhancing the reasoning capabilities of Large L...
arXiv:2604.14974v1 Announce Type: new Abstract: You are a robot and you live in a Markov decision process (MDP) with a finite or an infinite number of transitio...
arXiv:2604.15016v1 Announce Type: new Abstract: EEG foundation models (FMs) achieve strong cross-subject and cross-task generalization but impose substantial co...
arXiv:2604.15069v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) conventionally rely on standard Laplacian or adjacency matrices for structural mess...
arXiv:2604.15115v1 Announce Type: new Abstract: Most existing Byzantine-robust federated learning (FL) methods suffer from slow and unstable convergence.
arXiv:2604.15167v1 Announce Type: new Abstract: Post-training quantization (PTQ) assumes that a well-converged model is a quantization-ready model.
arXiv:2604.15169v1 Announce Type: new Abstract: Oil and gas drilling operations generate extensive time-series data from surface sensors, yet accurate real-time...
arXiv:2604.15180v1 Announce Type: new Abstract: Sparse attention has been proposed as a way to alleviate the quadratic cost of transformers, a central bottlenec...
arXiv:2604.15181v1 Announce Type: new Abstract: Extrapolative prediction of complex nonlinear dynamics remains a central challenge in engineering.
arXiv:2604.15201v1 Announce Type: new Abstract: As reinforcement learning (RL) deployments expand into safety-critical domains, existing evaluation methods fail...
arXiv:2604.15242v1 Announce Type: new Abstract: We study the problem of learning minimax policies in zero-sum matrix games. Fiegel et al.
arXiv:2604.15273v1 Announce Type: new Abstract: Node embeddings act as the information interface for graph neural networks, yet their empirical impact is often...
arXiv:2604.15297v1 Announce Type: new Abstract: MLP is a heavily used backbone in modern deep learning (DL) architectures for supervised learning on tabular dat...
arXiv:2512.22174v2 Announce Type: cross Abstract: Large Language Models (LLMs) deployed in practical and safety-critical settings are increasingly susceptible t...
arXiv:2604.05312v1 Announce Type: cross Abstract: A deep neural network (DNN) has been developed to accurately predict nuclear charge density distributions for...
arXiv:2604.14162v1 Announce Type: cross Abstract: Authors often struggle to interpret peer review feedback, deriving false hope from polite comments or feeling...
arXiv:2604.14174v1 Announce Type: cross Abstract: Alignment-tuned language models frequently suppress factual log-probabilities on politically sensitive topics...
arXiv:2604.14191v1 Announce Type: cross Abstract: State Space Models (SSMs) such as Mamba have become a popular alternative to Transformer models, due to their...
arXiv:2604.14208v1 Announce Type: cross Abstract: This work develops machine learning approaches to classify structured light wave beams developing random speck...
arXiv:2604.14233v1 Announce Type: cross Abstract: The IEC-61850 GOOSE protocol underpins time-critical communication in modern digital substations but lacks nat...
arXiv:2604.14241v1 Announce Type: cross Abstract: The classic paradigm of structural biology is that the sequence of a biomolecule (protein, nucleic acid, lipid...
arXiv:2604.14259v1 Announce Type: cross Abstract: Functional magnetic resonance imaging (fMRI) is widely used for studying and diagnosing brain disorders, with...
arXiv:2604.14263v1 Announce Type: cross Abstract: Accurate detection and segmentation of glomeruli in kidney tissue are essential for diagnostic applications.
arXiv:2604.14305v1 Announce Type: cross Abstract: Targeted amplicon panels are widely used in oncology diagnostics, but providing per-gene performance guarantee...
arXiv:2604.14322v1 Announce Type: cross Abstract: We derive a robust update rule for the online infinite hidden Markov model (iHMM) for when the streaming data...
arXiv:2604.14352v1 Announce Type: cross Abstract: Online A/B testing at scale relies on proxy metrics -- short-term, easily-measured signals used in place of sl...
arXiv:2604.14370v1 Announce Type: cross Abstract: AI tools increasingly guide targeted interventions in healthcare, education, and recruiting.
arXiv:2604.14398v1 Announce Type: cross Abstract: Rotating detonation engines (RDEs) are a promising propulsion concept that may offer higher thermodynamic effi...
arXiv:2604.14433v1 Announce Type: cross Abstract: Zero-ablation -- replacing token activations with zero vectors -- is widely used to probe token function in vi...
arXiv:2604.14460v1 Announce Type: cross Abstract: Neuromotor decoding from upper-limb electromyography (sEMG) can enhance human-machine interfaces and offer a m...
arXiv:2604.14507v1 Announce Type: cross Abstract: As a classic vision task, anomaly detection has been widely applied in industrial inspection and medical imagi...
arXiv:2604.14548v1 Announce Type: cross Abstract: As speech language models (SLMs) transition from personal devices into shared, multi-user environments, their...
arXiv:2604.14552v1 Announce Type: cross Abstract: Modern datacenters increasingly rely on low-power, single-slot inference accelerators to balance performance,...
arXiv:2604.14603v1 Announce Type: cross Abstract: The fundamental limit of natural signal compression has traditionally been characterized by classical rate-dis...
arXiv:2604.14614v1 Announce Type: cross Abstract: We give an algorithm for PAC learning intersections of $k$ halfspaces with a $\rho$ margin to within error $\v...
arXiv:2604.14619v1 Announce Type: cross Abstract: In computational paralinguistics, detecting cognitive load and deception from speech signals is a heavily rese...
arXiv:2604.14621v1 Announce Type: cross Abstract: Conformal prediction (CP) has attracted broad attention as a simple and flexible framework for uncertainty qua...
arXiv:2604.14630v1 Announce Type: cross Abstract: Recent advances in unsupervised video object segmentation have highlighted the potential of two-stream archite...
arXiv:2604.14643v1 Announce Type: cross Abstract: Adversarial attacks pose a severe threat to the reliability of deep learning models in remote sensing (RS) ima...
arXiv:2604.14644v1 Announce Type: cross Abstract: The inability to filter out in advance all potentially problematic data from the pre-training of large languag...
arXiv:2604.14724v1 Announce Type: cross Abstract: Vision State Space Models (SSMs) like Vim, VMamba, and SiMBA rely on complex scanning strategies to adapt sequ...
arXiv:2604.14725v1 Announce Type: cross Abstract: Recent advances in query optimization have shifted from traditional rule-based and cost-based techniques towar...
arXiv:2604.14732v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for building embodied agents that gro...
arXiv:2604.14751v1 Announce Type: cross Abstract: The communication bottleneck in federated learning (FL) has spurred extensive research into techniques to redu...
arXiv:2604.14787v1 Announce Type: cross Abstract: Network Digital Twins (NDTs) enable safe what-if analysis for 6G cloud-edge infrastructures, but adoption is o...
arXiv:2604.14796v1 Announce Type: cross Abstract: Proteins carry out biological functions through the coordinated action of groups of residues organized into st...
arXiv:2604.14809v1 Announce Type: cross Abstract: We study a classification problem with three key challenges: pervasive informative missingness, the integratio...
arXiv:2604.14810v1 Announce Type: cross Abstract: In online clustering problems, there is often a large amount of uncertainty over possible cluster assignments...
arXiv:2604.14825v1 Announce Type: cross Abstract: We present Nautilus, a novel tensor compiler that moves toward fully automated math-to-kernel optimization.
arXiv:2604.14860v1 Announce Type: cross Abstract: We study bandit best-arm identification with arbitrary and potentially adversarial rewards.
arXiv:2604.14876v1 Announce Type: cross Abstract: We study the tail behavior of regret in stochastic multi-armed bandits for algorithms that are asymptotically...
arXiv:2604.14882v1 Announce Type: cross Abstract: Rapid urbanization and continuous population growth have made municipal solid waste management increasingly ch...
arXiv:2604.14906v1 Announce Type: cross Abstract: The SARS-CoV-2 RNA pseudoknot is a promising target for antiviral intervention, as it regulates the efficiency...
arXiv:2604.14907v1 Announce Type: cross Abstract: Online hate speech and abusive language pose a growing challenge for content moderation, especially in multili...
arXiv:2604.14931v1 Announce Type: cross Abstract: Concatenating quantum error correction codes scales error correction capability by driving logical error rates...
arXiv:2604.14949v1 Announce Type: cross Abstract: In this paper, we proposed Bayesian Tucker decomposition (BTuD) in which residual is supposed to obey Gaussian...
arXiv:2604.14957v1 Announce Type: cross Abstract: Network security is a critical concern in the digital landscape of today, with users demanding secure browsing...
arXiv:2604.15075v1 Announce Type: cross Abstract: Open-weight Small Language Models(SLMs) can provide faster local inference at lower financial cost, but may no...
arXiv:2604.15096v1 Announce Type: cross Abstract: Echocardiography is a widely used modality for cardiac assessment due to its non-invasive and cost-effective n...
arXiv:2604.15101v1 Announce Type: cross Abstract: Learning-to-Rank (LTR) is a supervised machine learning approach that constructs models specifically designed...
arXiv:2604.15107v1 Announce Type: cross Abstract: Feature selection is a classical problem in statistics and machine learning, and it continues to remain an ext...
arXiv:2604.15171v1 Announce Type: cross Abstract: Recent work has shown that diffusion models trained with the denoising score matching (DSM) objective often vi...
arXiv:2604.15214v1 Announce Type: cross Abstract: Quantum kernel methods are among the leading candidates for achieving quantum advantage in supervised learning...
arXiv:2604.15216v1 Announce Type: cross Abstract: Mobility in urban and interurban areas, mainly by cars, is a day-to-day activity of many people.
arXiv:2604.15238v1 Announce Type: cross Abstract: This paper investigates continuous-time and discrete-time firing-rate and Hopfield recurrent neural networks (...
arXiv:2604.15269v1 Announce Type: cross Abstract: The impossibility of simultaneously cloning non-orthogonal states lies at the foundations of quantum theory.
arXiv:2604.15285v1 Announce Type: cross Abstract: We study post-training interpretability for Support Vector Machines (SVMs) built from truncated orthogonal pol...
arXiv:2210.09817v3 Announce Type: replace Abstract: In this paper, we describe a universal method for extracting the underlying monotonic trend factor from time...
arXiv:2211.16780v4 Announce Type: replace Abstract: In online incremental learning, data continuously arrives with substantial distributional shifts, creating a...
arXiv:2407.00809v3 Announce Type: replace Abstract: This paper introduces the Kernel Neural Operator (KNO), a provably convergent operator-learning architecture...
arXiv:2410.08329v3 Announce Type: replace Abstract: Computational wave imaging (CWI) extracts hidden structure and physical properties of a volume of material b...
arXiv:2411.00361v4 Announce Type: replace Abstract: Hierarchical reinforcement learning (HRL) enables agents to solve complex, long-horizon tasks by decomposing...
arXiv:2411.05472v2 Announce Type: replace Abstract: The paradigm shift toward structure-driven molecule generation has been propelled by advances in deep genera...
arXiv:2501.09331v3 Announce Type: replace Abstract: A machine that learns a task from observations must encounter and process uncertainty and novelty, especiall...
arXiv:2501.11711v2 Announce Type: replace Abstract: The COVID-19 pandemic has claimed millions of lives, spurring the development of diverse forecasting models.
arXiv:2505.10846v3 Announce Type: replace Abstract: This paper presents AutoRAN, the first framework to automate the hijacking of internal safety reasoning in l...
arXiv:2505.11017v2 Announce Type: replace Abstract: Time series forecasting is critical across multiple domains, where time series data exhibit both local patte...
arXiv:2505.13754v3 Announce Type: replace Abstract: We present the first unsupervised learning model for Maximum-Independent-Set (MaxIS) in dynamic graphs where...
arXiv:2505.20761v3 Announce Type: replace Abstract: While the performance of machine learning systems has experienced significant improvement in recent years, r...
arXiv:2509.12760v4 Announce Type: replace Abstract: We introduce the Similarity-Distance-Magnitude (SDM) activation function, a more robust and interpretable fo...
arXiv:2509.12833v2 Announce Type: replace Abstract: Projection-based safety filters, which modify unsafe actions by mapping them to the closest safe alternative...
arXiv:2509.23249v4 Announce Type: replace Abstract: It is often possible to perform reduced order modelling by specifying linear subspace which accurately captu...
arXiv:2509.23638v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models face memory and PCIe latency bottlenecks when deployed on commodity hardware...
arXiv:2509.24886v3 Announce Type: replace Abstract: Canonicalization is a widely used strategy in equivariant machine learning, enforcing symmetry in neural net...
arXiv:2510.08055v2 Announce Type: replace Abstract: Large Language Model (LLM) inference in production must meet stringent service-level objectives for both tim...
arXiv:2510.25892v2 Announce Type: replace Abstract: We propose a graph-topological approach to active learning that directly targets the core challenge of explo...
arXiv:2510.26109v4 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has significantly boosted the reasoning capability of...
arXiv:2511.15915v2 Announce Type: replace Abstract: We present AccelOpt, a self-improving large language model (LLM) agentic system that autonomously optimizes...
arXiv:2511.18107v2 Announce Type: replace Abstract: Accurately solving partial differential equations (PDEs) is critical to understanding complex scientific and...
arXiv:2512.07222v4 Announce Type: replace Abstract: To address the trade-off between robustness and performance for robust VLM, we observe that function words c...
arXiv:2512.14098v3 Announce Type: replace Abstract: Any-to-Any models are an emerging class of multimodal models that accept combinations of text and multimodal...
arXiv:2512.22897v3 Announce Type: replace Abstract: Spectral clustering has emerged as one of the most effective clustering algorithms due to its superior perfo...
arXiv:2601.02997v2 Announce Type: replace Abstract: Large language models (LLMs) excel in program synthesis, yet their capacity for neural architecture design -...
arXiv:2601.10237v2 Announce Type: replace Abstract: Differentially Private Stochastic Gradient Descent (DP-SGD) is the dominant paradigm for private training, b...
arXiv:2601.12145v2 Announce Type: replace Abstract: Softmax attention struggles with long contexts due to structural limitations: the strict sum-to-one constrai...
arXiv:2602.06930v2 Announce Type: replace Abstract: We study off-policy reinforcement learning for controlling continuous-time Markov diffusion processes with d...
arXiv:2602.07529v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong performance and rapid progress in a wide range of medi...
arXiv:2602.07618v3 Announce Type: replace Abstract: We investigate the approximation capabilities of dense neural networks.
arXiv:2602.20370v2 Announce Type: replace Abstract: The universal approximation theorem establishes that neural networks can approximate any continuous function...
arXiv:2603.09923v3 Announce Type: replace Abstract: The Exponential Moving Average (EMA) is a cornerstone of widely used optimizers such as Adam.
arXiv:2603.20997v2 Announce Type: replace Abstract: We identify a routing paradox in hybrid sequence models: content-based routing - deciding which tokens deser...
arXiv:2603.22564v2 Announce Type: replace Abstract: Understanding cellular trajectories via time-resolved single-cell transcriptomics is vital for studying deve...
arXiv:2604.07663v2 Announce Type: replace Abstract: The AdamW optimizer, while standard for LLM pretraining, is a critical memory bottleneck, consuming optimize...
arXiv:2604.11198v3 Announce Type: replace Abstract: Accurate air traffic prediction in the terminal airspace (TA) is pivotal for proactive air traffic managemen...
arXiv:2604.11529v2 Announce Type: replace Abstract: Foundation models have transformed natural language processing and computer vision, and a rapidly growing li...
arXiv:2604.13861v2 Announce Type: replace Abstract: This paper develops a unified Markov Decision Process (MDP) framework for optimising two recurring in-match...
arXiv:2604.13878v2 Announce Type: replace Abstract: Driver drowsiness significantly impairs the ability to accurately judge safe braking distances and is estima...
arXiv:2311.11841v4 Announce Type: replace-cross Abstract: We consider the stochastic gradient method with random reshuffling ($\mathsf{RR}$) for tackling smooth...
arXiv:2410.05882v3 Announce Type: replace-cross Abstract: Respiratory motion complicates accurate irradiation of thoraco-abdominal tumors during radiotherapy, a...
arXiv:2502.21029v2 Announce Type: replace-cross Abstract: Reliable localization of people is fundamental for service and social robots that must operate in clos...
arXiv:2503.21432v2 Announce Type: replace-cross Abstract: We propose a method to explore the flavor structure of leptons using diffusion models, which are known...
arXiv:2505.02979v3 Announce Type: replace-cross Abstract: We propose a novel inverse-modelling approach which estimates the parameters of a simple land-surface...
arXiv:2506.00433v4 Announce Type: replace-cross Abstract: High-resolution image synthesis remains a core challenge in generative modeling, particularly in balan...
arXiv:2506.08080v2 Announce Type: replace-cross Abstract: Particle physics theories, such as those which explain neutrino flavor mixing, arise from a vast lands...
arXiv:2506.09457v3 Announce Type: replace-cross Abstract: Direct Alignment Algorithms (DAAs), such as Direct Preference Optimization (DPO) and Simple Preference...
arXiv:2506.13139v2 Announce Type: replace-cross Abstract: Modern Machine Learning (ML) and Deep Neural Networks (DNNs) often operate on high-dimensional data an...
arXiv:2506.13408v2 Announce Type: replace-cross Abstract: Accurate channel estimation is critical for high-performance Orthogonal Frequency-Division Multiplexin...
arXiv:2506.14844v2 Announce Type: replace-cross Abstract: Inter reader variability and cross site domain shift challenge the automatic segmentation of prostate...
arXiv:2509.01728v4 Announce Type: replace-cross Abstract: Recent advances in the development of robotic foundation models have led to promising end-to-end and g...
arXiv:2509.23391v3 Announce Type: replace-cross Abstract: Machine learning has become a fundamental approach for modeling, prediction, and control, enabling sys...
arXiv:2510.02738v3 Announce Type: replace-cross Abstract: While visuomotor policy has made advancements in recent years, contact-rich tasks still remain a chall...
arXiv:2511.10909v2 Announce Type: replace-cross Abstract: Modern AI accelerators rely on matrix multiply-accumulate units (MMAUs), such as NVIDIA Tensor Cores a...
arXiv:2601.12407v2 Announce Type: replace-cross Abstract: As LLMs rapidly advance and enter real-world use, their privacy implications are increasingly importan...
arXiv:2602.14517v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have achieved strong results in mathematical reasoning, and are increasin...
arXiv:2602.22699v2 Announce Type: replace-cross Abstract: SQL is the de facto interface for exploratory data analysis;
arXiv:2603.06431v2 Announce Type: replace-cross Abstract: Neural network methods for PDEs require reliable error control in function space norms.
arXiv:2603.10992v3 Announce Type: replace-cross Abstract: Building local surrogates to accelerate stationary point searches on potential energy surfaces spans d...
arXiv:2604.01197v2 Announce Type: replace-cross Abstract: Learning quantum states from measurement data is a central problem in quantum information and computat...
arXiv:2604.05478v3 Announce Type: replace-cross Abstract: Immune checkpoint inhibitors (ICIs) have transformed cancer therapy;
arXiv:2604.09982v2 Announce Type: replace-cross Abstract: Reproducibility must validate architectural robustness, not just numerical accuracy.
arXiv:2604.11496v2 Announce Type: replace-cross Abstract: Dual-encoder Vision-Language Models (VLMs) such as CLIP are often characterized as bag-of-words system...
arXiv:2604.13315v2 Announce Type: replace-cross Abstract: High-resolution data in spatial and temporal contexts is imperative for developing climate resilient c...
arXiv:2604.14193v1 Announce Type: new Abstract: Human 3D vision involves two distinct stages: an Experience Module, where stereo depth is extracted relative to...
arXiv:2604.14268v1 Announce Type: new Abstract: We introduce HY-World 2.0, a multi-modal world model framework that advances our prior project HY-World 1.0.
arXiv:2604.14302v1 Announce Type: new Abstract: We tackle a new problem: generating geometrically consistent multi-view scenes from a single freehand sketch.
arXiv:2604.14329v1 Announce Type: new Abstract: Non-violent street robberies (snatch-and-run) are difficult to detect automatically because they are brief, subt...
arXiv:2604.14388v1 Announce Type: new Abstract: Humans routinely infer taste, smell, texture, and even sound from food images a phenomenon well studied in cogni...
arXiv:2604.14506v1 Announce Type: new Abstract: Masked image modeling (MIM) is a highly effective self-supervised learning (SSL) approach to extract useful feat...
arXiv:2604.14520v1 Announce Type: new Abstract: Omni-modal Large Language Models (Omni-MLLMs) promise a unified integration of diverse sensory streams.
arXiv:2604.14526v1 Announce Type: new Abstract: Existing single-modal RGB trackers often face performance bottlenecks in complex dynamic scenes, while the intro...
arXiv:2604.14527v1 Announce Type: new Abstract: A low cost fluorescence-based optical system is developed for detecting the presence of certain microorganisms a...
arXiv:2604.14540v1 Announce Type: new Abstract: Detecting slow-moving landslides directly from wrapped Interferometric Synthetic Aperture Radar (InSAR) interfer...
arXiv:2604.14541v1 Announce Type: new Abstract: We present a framework for explicit emotion control in feed-forward, single-image 3D head avatar reconstruction.
arXiv:2604.14558v1 Announce Type: new Abstract: This paper presents the NTIRE 2026 image super-resolution ($\times$4) challenge, one of the associated competiti...
arXiv:2604.14560v1 Announce Type: new Abstract: Video face restoration aims to enhance degraded face videos into high-quality results with realistic facial deta...
arXiv:2604.14563v1 Announce Type: new Abstract: Vision Transformer (ViT)-based sparse multi-view 3D object detectors have achieved remarkable accuracy but still...
arXiv:2604.14568v1 Announce Type: new Abstract: Visual reasoning models (VRMs) have recently shown strong cross-modal reasoning capabilities by integrating visu...
arXiv:2604.14570v1 Announce Type: new Abstract: Deepfake detectors face growing challenges in generalization as new image synthesis techniques emerge.
arXiv:2604.14574v1 Announce Type: new Abstract: With the rapid advancement of deep learning in image generation, facial forgery techniques have achieved unprece...
arXiv:2604.14580v1 Announce Type: new Abstract: Existing audio-driven video digital human generation models rely on multi-step denoising, resulting in substanti...
arXiv:2604.14582v1 Announce Type: new Abstract: High-resolution (HR) land-cover mapping is often constrained by the high cost of dense HR annotations.
arXiv:2604.14591v1 Announce Type: new Abstract: We address the problem of prompt-guided image editing in visual autoregressive models.
arXiv:2604.14605v1 Announce Type: new Abstract: Graphic design creation involves harmoniously assembling multimodal components such as images, text, logos, and...
arXiv:2604.14622v1 Announce Type: new Abstract: In this work, we propose a Multigrain-aware Semantic Prototype Scanning paradigm for pan-sharpening, built upon...
arXiv:2604.14629v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have shown remarkable capabilities in joint vision-language understanding, but the...
arXiv:2604.14632v1 Announce Type: new Abstract: Conventional RGB-based high dynamic range (HDR) imaging faces a fundamental trade-off between motion artifacts i...
arXiv:2604.14684v1 Announce Type: new Abstract: Visual prompted object detection enables interactive and flexible definition of target categories, thereby facil...
arXiv:2604.14692v1 Announce Type: new Abstract: Video understanding requires identifying and reasoning over semantically discriminative visual objects across fr...
arXiv:2604.14703v1 Announce Type: new Abstract: Although some existing image manipulation localization (IML) methods incorporate authenticity-related supervisio...
arXiv:2604.14706v1 Announce Type: new Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have enabled highly efficient and photorealistic novel view synt...
arXiv:2604.14710v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) aims to retrieve target images by integrating a reference image with a correspond...
arXiv:2604.14711v1 Announce Type: new Abstract: Structural damage detection is essential for maintaining the safety and reliability of civil infrastructure.
arXiv:2604.14720v1 Announce Type: new Abstract: Myotubes are multinucleated muscle fibers serving as key model systems for studying muscle physiology, disease m...
arXiv:2604.14734v1 Announce Type: new Abstract: Morphing is a challenge to face recognition (FR) for which several morphing attack detection solutions have been...
arXiv:2604.14747v1 Announce Type: new Abstract: Solving non-linear least-squares problem for pose estimation (rotation and translation) is often a time consumin...
arXiv:2604.14755v1 Announce Type: new Abstract: Early identification and removal of polyps can reduce the risk of developing colorectal cancer.
arXiv:2604.14762v1 Announce Type: new Abstract: Generalized Category Discovery (GCD) challenges methods to identify known and novel classes using partially labe...
arXiv:2604.14779v1 Announce Type: new Abstract: In continual visual question answering (VQA), existing Continual Learning (CL) methods are mostly built for symm...
arXiv:2604.14781v1 Announce Type: new Abstract: Obstacle detection in railway environments is crucial for ensuring safety.
arXiv:2604.14782v1 Announce Type: new Abstract: We propose a compositional method for constructing a complete 3D head avatar from a single image.
arXiv:2604.14805v1 Announce Type: new Abstract: Grain-edge segmentation (GES) and lithology semantic segmentation (LSS) are two pivotal tasks for quantifying ro...
arXiv:2604.14816v1 Announce Type: new Abstract: This paper presents an overview of the NTIRE 2026 Challenge on Video Saliency Prediction.
arXiv:2604.14837v1 Announce Type: new Abstract: Alzheimer's disease (AD) confirmation often relies on positron emission tomography (PET) or cerebrospinal fluid...
arXiv:2604.14874v1 Announce Type: new Abstract: Most state-of-the-art vein recognition methods rely on closed-set classification, which inherently limits their...
arXiv:2604.14884v1 Announce Type: new Abstract: Small object detection remains a significant challenge due to feature degradation from downsampling, mutual occl...
arXiv:2604.14910v1 Announce Type: new Abstract: Achieving high-fidelity generation in extremely few sampling steps has long been a central goal of generative mo...
arXiv:2604.14914v1 Announce Type: new Abstract: Text-driven inversion of generative models is a core paradigm for manipulating 2D or 3D content, unlocking numer...
arXiv:2604.14928v1 Announce Type: new Abstract: We introduce a hybrid Gaussian-hash-grid radiance representation for reconstructing 2D Gaussian scene models fro...
arXiv:2604.14933v1 Announce Type: new Abstract: Skeleton-based human action recognition is a powerful approach for understanding human behaviour from pose data,...
arXiv:2604.14953v1 Announce Type: new Abstract: Gesture recognition research, unlike NLP, continues to face acute data scarcity, with progress constrained by th...
arXiv:2604.14958v1 Announce Type: new Abstract: Few-shot fine-grained image classification aims to recognize subcategories with high visual similarity using onl...
arXiv:2604.15003v1 Announce Type: new Abstract: The rapid rise of image-to-video (I2V) generation enables realistic videos to be created from a single image but...
arXiv:2604.15027v1 Announce Type: new Abstract: Significant progress has been made in detecting synthetic images, however most existing approaches operate on a...
arXiv:2604.15047v1 Announce Type: new Abstract: Implicit neural representations (INRs) mark a fundamental shift in signal modeling, moving from discrete sampled...
arXiv:2604.15059v1 Announce Type: new Abstract: Motion artifacts present a significant challenge in structural MRI (sMRI), often compromising clinical diagnosti...
arXiv:2604.15065v1 Announce Type: new Abstract: Transformer-based detectors have advanced small-object detection, but they often remain inefficient and vulnerab...
arXiv:2604.15088v1 Announce Type: new Abstract: Building extraction from optical Remote Sensing (RS) imagery suffers from performance degradation under real-wor...
arXiv:2604.15090v1 Announce Type: new Abstract: Any-Time Person Re-identification (AT-ReID) necessitates the robust retrieval of target individuals under arbitr...
arXiv:2604.15134v1 Announce Type: new Abstract: Reliable procedural monitoring in video requires exposure to naturally occurring human errors and the recoveries...
arXiv:2604.15141v1 Announce Type: new Abstract: Higher-order learning is fundamentally rooted in exploiting compositional features.
arXiv:2604.15170v1 Announce Type: new Abstract: Adverse lighting conditions, such as cast shadows and irregular illumination, pose significant challenges to com...
arXiv:2604.15173v1 Announce Type: new Abstract: Temporal action segmentation (TAS) demands dense temporal supervision, yet most of the annotation cost in untrim...
arXiv:2604.15196v1 Announce Type: new Abstract: We propose a novel hierarchical spatiotemporal vector quantization framework for unsupervised skeleton-based tem...
arXiv:2604.15237v1 Announce Type: new Abstract: Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory...
arXiv:2604.15239v1 Announce Type: new Abstract: In this work, we revisit several key design choices of modern Transformer-based approaches for feed-forward 3D G...
arXiv:2604.15281v1 Announce Type: new Abstract: 3D policy learning promises superior generalization and cross-embodiment transfer, but progress has been hindere...
arXiv:2604.15284v1 Announce Type: new Abstract: The efficient spatial allocation of primitives serves as the foundation of 3D Gaussian Splatting, as it directly...
arXiv:2604.15299v1 Announce Type: new Abstract: Video generation has advanced rapidly, with recent methods producing increasingly convincing animated results.
arXiv:2604.15301v1 Announce Type: new Abstract: Many SLT systems quietly assume that brief chunks of signing map directly to spoken-language words.
arXiv:2604.15308v1 Announce Type: new Abstract: High-level autonomous driving requires motion planners capable of modeling multimodal future uncertainties while...
arXiv:2604.15310v1 Announce Type: new Abstract: This paper presents a method for image relighting that enables precise and continuous control over multiple illu...
arXiv:2604.15311v1 Announce Type: new Abstract: This paper focuses on the alignment of flow matching models with human preferences.
arXiv:2604.15312v1 Announce Type: new Abstract: Conventional frame-based cameras capture rich contextual information but suffer from limited temporal resolution...
arXiv:2604.14454v1 Announce Type: cross Abstract: Autonomous vehicles equipped with robust onboard perception, localization, and planning still face limitations...
arXiv:2604.14799v1 Announce Type: cross Abstract: Effective abstention (EA), recognizing evidence insufficiency and refraining from answering, is critical for r...
arXiv:2604.14800v1 Announce Type: cross Abstract: Objective. Standard Magnetic Resonance Imaging (MRI) reconstruction pipelines discard phase information captur...
arXiv:2604.14944v1 Announce Type: cross Abstract: We present HRDexDB, a large-scale, multi-modal dataset of high-fidelity dexterous grasping sequences featuring...
arXiv:2604.14973v1 Announce Type: cross Abstract: A vision foundation model outputs an embedding vector for an image, which can be affected by common editing op...
arXiv:2604.15086v1 Announce Type: cross Abstract: Recent advances in video-to-audio (V2A) generation enable high-quality audio synthesis from visual content, ye...
arXiv:2604.15221v1 Announce Type: cross Abstract: We propose a framework for vision-based human pose estimation and motion prediction that gives conformal predi...
arXiv:2411.09209v5 Announce Type: replace Abstract: Audio-driven portrait animation has made significant advances with diffusion-based models, improving video q...
arXiv:2503.21970v3 Announce Type: replace Abstract: State-Space Models (SSMs) have attracted considerable attention in Image Restoration (IR) due to their abili...
arXiv:2504.16455v2 Announce Type: replace Abstract: Transformer-based networks have achieved strong performance in low-level vision tasks like image deraining b...
arXiv:2505.03093v3 Announce Type: replace Abstract: Forest inventories rely on accurate measurements of the diameter at breast height (DBH) for ecological monit...
arXiv:2505.18129v3 Announce Type: replace Abstract: Reinforcement learning (RL) is becoming an important direction for post-training vision-language models (VLM...
arXiv:2505.20122v2 Announce Type: replace Abstract: This paper introduces MEBench, a novel benchmark for evaluating mutual exclusivity (ME) bias, a cognitive ph...
arXiv:2505.20291v4 Announce Type: replace Abstract: Text-to-image retrieval (T2I retrieval) remains challenging because cross-modal embeddings often behave as b...
arXiv:2506.14121v2 Announce Type: replace Abstract: Face super-resolution (FSR) under limited computational budgets remains challenging.
arXiv:2509.15602v5 Announce Type: replace Abstract: Multimodal large language models (MLLMs) excel at general video understanding but struggle with fast, high-f...
arXiv:2510.17568v5 Announce Type: replace Abstract: Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong ca...
arXiv:2510.18935v3 Announce Type: replace Abstract: Earth observation involves collecting, analyzing, and processing an ever-growing mass of data.
arXiv:2511.07412v2 Announce Type: replace Abstract: Developing embodied AI for intelligent surgical systems requires safe, controllable environments for continu...
arXiv:2511.20645v2 Announce Type: replace Abstract: Latent-space modeling has been the standard for Diffusion Transformers (DiTs).
arXiv:2511.21025v2 Announce Type: replace Abstract: Image captions serve as efficient surrogates for visual content in multimodal systems such as retrieval, rec...
arXiv:2512.00995v3 Announce Type: replace Abstract: Part-level point cloud segmentation has recently attracted significant attention in 3D computer vision.
arXiv:2512.04585v4 Announce Type: replace Abstract: Segment Anything Model 3 (SAM3) advances open-vocabulary segmentation through promptable concept segmentatio...
arXiv:2512.13671v2 Announce Type: replace Abstract: Industrial anomaly detection (IAD) is challenging due to the subtle and highly localized nature of many defe...
arXiv:2512.22185v2 Announce Type: replace Abstract: Intracranial aneurysm rupture causes subarachnoid hemorrhage with mortality near 50%, making early detection...
arXiv:2601.03416v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have become widely deployed, yet their safety alignment remains fra...
arXiv:2601.04567v2 Announce Type: replace Abstract: Harmful memes are ever-shifting in the Internet communities, which are difficult to analyze due to their typ...
arXiv:2601.04588v2 Announce Type: replace Abstract: Segmentation of the left atrial (LA) wall and endocardium from late gadolinium-enhanced (LGE) MRI is essenti...
arXiv:2601.06559v2 Announce Type: replace Abstract: Grounding events in videos serves as a fundamental capability in video analysis.
arXiv:2601.08831v5 Announce Type: replace Abstract: Video object segmentation methods like SAM2 achieve strong performance through memory-based architectures bu...
arXiv:2601.09240v2 Announce Type: replace Abstract: Satellite videos provide continuous observations of surface dynamics but pose significant challenges for mul...
arXiv:2602.20328v2 Announce Type: replace Abstract: Inverse problems in imaging are ill-posed, leading to infinitely many solutions consistent with the measurem...
arXiv:2603.16024v2 Announce Type: replace Abstract: We introduce a speech-guided embodied agent framework for video-guided skull base surgery that dynamically e...
arXiv:2603.16869v2 Announce Type: replace Abstract: We introduce SegviGen, a framework that repurposes native 3D generative models for 3D part segmentation.
arXiv:2603.23284v2 Announce Type: replace Abstract: Spatiotemporal predictive learning aims to forecast future frames from historical observations in an unsuper...
arXiv:2603.24985v2 Announce Type: replace Abstract: Segmenting the left atrial wall from late gadolinium enhancement magnetic resonance images (MRI) is challeng...
arXiv:2603.24992v2 Announce Type: replace Abstract: Accurate segmentation of the left atrial (LA) wall in 3D late gadolinium-enhanced MRI (LGE-MRI) is essential...
arXiv:2604.00313v2 Announce Type: replace Abstract: Automated species classification from underwater imagery is bottlenecked by the cost of expert annotation, a...
arXiv:2604.00998v2 Announce Type: replace Abstract: Ground roll is a common type of coherent noise in seismic records, and its attenuation remains challenging d...
arXiv:2604.03611v2 Announce Type: replace Abstract: Portrait composition plays a central role in portrait aesthetics and visual communication, yet existing data...
arXiv:2604.05541v2 Announce Type: replace Abstract: Reliable interpretation of echocardiography (Echo) is crucial for assessing cardiac function, which demands...
arXiv:2604.07021v2 Announce Type: replace Abstract: Weakly supervised semantic segmentation aims to achieve pixel-level predictions using image-level labels.
arXiv:2604.09057v2 Announce Type: replace Abstract: Audio-video (AV) generation has recently made strong progress in perceptual quality and multimodal coherence...
arXiv:2604.10500v2 Announce Type: replace Abstract: Multimodal latent reasoning has emerged as a promising paradigm that replaces explicit Chain-of-Thought (CoT...
arXiv:2604.11176v2 Announce Type: replace Abstract: The biological definition of Alzheimer's disease (AD) relies on multi-modal neuroimaging, yet the clinical u...
arXiv:2604.11600v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress but continue to struggle with geo...
arXiv:2604.12580v2 Announce Type: replace Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have enabled impressive real-time photorealistic rendering.
arXiv:2604.13183v2 Announce Type: replace Abstract: Generalizable cross-view geo-localization aims to match the same location across views in unseen regions and...
arXiv:2604.13491v2 Announce Type: replace Abstract: With the rapid progress of Multimodal Large Language Models (MLLMs), unified MLLMs that jointly perform imag...
arXiv:2604.13596v2 Announce Type: replace Abstract: Instance-level object segmentation across disparate egocentric and exocentric views is a fundamental challen...
arXiv:2604.13660v2 Announce Type: replace Abstract: In Deepfake Detection (DFD) tasks, researchers proposed two types of MLLM-based methods: complementary combi...
arXiv:2604.13710v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) exhibit strong reasoning and world knowledge, yet adapting them for...
arXiv:2604.14041v2 Announce Type: replace Abstract: Daily scenarios are characterized by visual richness, requiring Multimodal Large Language Models (MLLMs) to...
arXiv:2604.14141v2 Announce Type: replace Abstract: Streaming 3D reconstruction aims to recover 3D information, such as camera poses and point clouds, from a vi...
arXiv:2604.14149v2 Announce Type: replace Abstract: Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensiv...
来论坛快十几天了，送了三波抽奖。 https://linux.do/t/topic/1951924/250 https://linux.do/t/topic/1953817/599 【YY小佬新人】codex 100个json免费送 第二波 福利羊毛 我用cloudfare，你好好看看教程~~ 现在开始送第四波！
各位佬友，遇到这种问题应该怎么解决？ 1 个帖子 - 1 位参与者 阅读完整话题
我发现一个问题，自己买了个claude max，然后用sub2api中转出来，用cc-switch配置上，和用官方版本的 web版本连github开发，体验根本不能比，web版本超级好用。
之前用deepseek的时候，一些觉得比较有用的对话都会建分组、拉收藏夹…… 偶尔遇上不记得想找的对话，也有搜索框…… 在用豆包的时候（我主要用网页版），发现居然不能收藏对话，也不提供搜索…… 各位有这样的问题吗？ 还是说我的版本不对？
哥哥们，我把json文件的默认打开方式从PyCharm改成了vscode，软件是生效了，但是文件logo还是显示PyCharm，请问怎么把logo也刷新一下呢？ 有什么原生方法可以刷新吗？或者借助第三方软件？
今天看了A社的发言才知道还有另一个上下文测试集——GraphWalks。我去用AI搜索了下两个测试集的指导场景。如果考虑A社的信用问题，GraphWalks和MRCRv2的使用场景分别在哪？ 1 个帖子 - 1 位参与者 阅读完整话题
古法注册了3个号，换着ip注册，发现都刷不出试用plus了，各位佬也是这样吗？ 5 个帖子 - 4 位参与者 阅读完整话题
试着生成了一个，感觉除了个别字体上的微小瑕疵，其他的几乎分辨不出来真假 6 个帖子 - 6 位参与者 阅读完整话题
我是自己用来科研绘图的，但是最近自己开的plus和team都被封号特别快，最快一次甚至开通后不到一个小时就被封号，请问有什么好的防封办法吗？跪谢 5 个帖子 - 5 位参与者 阅读完整话题
工作几年了，想发展发展副业，佬们有啥推荐，主后端（Java、Python）会前端（Vue React 会写不深入），接接单改善生活 9 个帖子 - 6 位参与者 阅读完整话题
用到4.7的第一反应是A\绝对蒸gpt了，之前用opus维护一些对外的文档就是看重它是这几家里面比较讲人话的，结果现在也开始出现gpt式的正反叙述了。这没蒸是真不信啊。 1 个帖子 - 1 位参与者 阅读完整话题
不过似乎现在只支持ultra会员，具体如图。 2 个帖子 - 2 位参与者 阅读完整话题
看了看新才的4.7opus，有人说拉了，有人说神了，感觉这么两极分化吗？所以开一下这个帖子。你可以把你想要测试的问题发过来，然后我会问我的官克API。目前测了 洗车问题，如果你的4.7回答错了，不用怀疑你被降智了。
Claude Code 使用了第三方 provider，auto-dream 模式能用吗。我在/dream 选项里面启用了，用了一周，好像没有响应过 2 个帖子 - 2 位参与者 阅读完整话题
刚在xhs看见有个帖子说gpt那些换token代充怎么搞的 就有人发到号商群里要求其他人去举报 我真是服了 代充方法不已经是在推特上面泛滥了吗 这帮号商还想捂在手里吗 2 个帖子 - 2 位参与者 阅读完整话题
这四个模型是同一个时代的产物？给我整笑了捏 笑得比真人还美，我死了 10 个帖子 - 9 位参与者 阅读完整话题
搞了好多公益站，想持续发展。结果都凉了 只能用古法注册，一个QQ号有三个邮箱，一个手机号有三个QQ号。 等一个天才程序员！！！想他的每一天。。。
如图，前几天发现codex开始能在对话中直接点开文件了，但是一直显示加载失败，windows的，请问是什么问题呢？ 1 个帖子 - 1 位参与者 阅读完整话题
本帖使用社区公益推广，符合推广要求。我申明并遵循社区要求的以下内容： 我的项目是免费使用的，无收费（变相收费、赞助）部分： 是 我的帖子已经打上 公益推广 标签： 是 我的项目属于个人项目，与公司或商业机构无关： 是 我的项目不存在QQ、TG等群组引流： 是 我的项目不存在非运营必要的网站引流： 是 我的项目不存在为他...
开个帖子交流下 Claude KYC 如何解决？ 我的账号：google 老号+家宽 ip 美国+google pay 支付，5x 的账号。之前一直稳定使用 2 个月，也没咋用满过基本上都是 50% 不到 之前把 google pay 续费取消了，昨天再次订阅完了之后就变成 free 了，需要验证 kyc 俺现在很纠结...
本帖使用社区开源推广，符合推广要求。我申明并遵循社区要求的以下内容： 我的帖子已经打上 开源推广 标签： 是 我的开源项目完整开源，无未开源部分： 是 我的开源项目已链接认可 LINUX DO 社区： 是 我帖子内的项目介绍，AI生成、润色内容部分已截图发出： 是 以上选择我承诺是永久有效的，接受社区和佬友监督： 是...
各位佬，请问cc封号后要怎么清理环境呢？害怕环境被标记导致后续秒封。另外google play的支付需要换新的账号吗？ 1 个帖子 - 1 位参与者 阅读完整话题
ccswicth里面的模型也选了5.3-codex 21 个帖子 - 8 位参与者 阅读完整话题
账号是5X的，本来打算pro随便撑完这个月的，下个月假期，结果出opus4.7了，想了想也没接着开20X，开的5X，下述额度都是基于5X,并且只使用opus4.7思考MAX 昨天刚出的时候 半夜重置了一次额度进行调整，今天上午的数据 可以看到原本 5 小时用满周限额是 6%，最新数据则变为 8% 实际额度，我没感觉出来...
听说有那种TG Bot搞得免费Plus,但好像有点麻烦,找到了一些代理商卖的差不多7-8块一个Plus,想问一下这种的一般能用多久以及额度多少 (听说奥特曼为了Pro砍了一点Plus额度) 11 个帖子 - 10 位参与者 阅读完整话题
就拿洗车问题提问 opus4.6的回答 opus4.7的回答 又测了一遍，这回有点反应过来了 gpt5.4的回答（看了各位佬友的gpt，感觉我的gpt是被降智了，奥特曼还我血汗钱） gemini pro的回答 12 个帖子 - 9 位参与者 阅读完整话题
如图，昨天CC更新到2.1.111以后，接口的报错信息都不展示了，之前是有红色的错误信息的，今天升到了2.1.112也还是没有 但是我试了下如果是网络错误还可以看到： 没有错误提示有点难受呀，用中转站的话连为啥用不了都不知道了，起码给个状态码呀。 5 个帖子 - 3 位参与者 阅读完整话题
跟坛子上的佬学习的羊毛脚本，但是搭建后一直没有用过。于是收到了上面的信件， 10 个帖子 - 9 位参与者 阅读完整话题
平常登5刀会直接触发限额，今天才一半，窗口变10刀了！！！感谢4.7让我用上更耐用的4.6 而且是5小时限额和周限一起翻倍，所以周限额现在是100刀！我的天呐a/大人，性价比拉满啊。 90r用满一个月至少400刀保底，你还花那冤枉钱买既不稳定也不便宜的中转？
自己的合法权益是合法的权益。 该吃饭的时候一定要能吃饭。
Learn how Github uses eBPF to detect and prevent circular dependencies in its deployment tooling.
3月份一线城市商品住宅销售价格环比上涨 二三线城市环比降幅收窄或相同 ——国家统计局城市司首席统计师王中华解读2026年3月份商品住宅销售价格变动情况统计数据 2026年3月份，70个大中城市中，一线城市商品住宅销售价格环比上涨，二三线城市环比降幅收窄或相同。新建商品住宅和二手住宅销售价格环比上涨城市个数...
这可能是互联网最奇怪的一场官司之一。一个月前《安娜的档案被 13 家大型出版商联合起诉》，如今判决已经出来了：没有出庭、没有抗辩，安娜的档案直接败诉。 法院判决其赔偿3.22亿美元，并下达永久禁令，要求域名注册商及相关服务提供方停止为该网站提供支持，包括暂停其域名的解析与使用。
（2026年4月16日） 每日经济新闻记者： 尽管国际环境跌宕起伏，我国一季度主要经济指标仍然表现良好，请问您如何评价一季度的经济运行总体表现？主要原因是什么？谢谢。 毛盛勇： 谢谢您的提问。从刚才介绍的情况来看，今年一季度我国经济实现了良好开局，国内生产总值同比增长5%，比去年四季度...
复现一篇论文，你通常要花多久？配环境、装依赖、改 Bug，一通折腾下来，一周起步。现在，这件事，已经可以交给 AI 自动完成了。而且，是一只“龙虾”。 最近 AI 圈最火的莫过于那只无所不能的龙虾 OpenClaw，已经被复旦 NLP 团队悄悄塞进了一个科研工具里： 不少人还在苦恼如何配置复杂的环境
Cloudflare Mesh 是 Cloudflare 刚刚发布的私有网络功能，与 Tailscale、Zerotier 类似，可以将不同设备接入私有网络，并且通过专用 IP 互相通信。流量全部经由 Cloudflare 网络。 与 Tailscale、Zerotier 有什么不同？
嫌弃短视频浪费时间的用户终于有救了！YouTube 已经上线新功能，允许用户在设置 > 时间管理中，将 Shorts 的每日上限设置为 0 分钟，即：允许用户彻底关闭 Shorts。@Appinn 如何关闭 Shorts 需要在手机端的 Youtube 上，才可以设置。 具体为： 设置 > 时间管理
Nature, Published online: 16 April 2026; doi:10.1038/d41586-026-01212-5 Modelling suggests that the layer beneath the planet’s acidic clouds is comprised of par...
Nature, Published online: 16 April 2026; doi:10.1038/d41586-026-01210-7 Most of the individuals in a seventeenth-century-Switzerland burial site had performed s...
Nature, Published online: 16 April 2026; doi:10.1038/d41586-026-01213-4 Study of gene expression also finds age-related increases in men’s vulnerability to cert...
Nature, Published online: 16 April 2026; doi:10.1038/d41586-026-01134-2 Many Democrats making the switch to politics are motivated by the Trump administration’s...
Nature, Published online: 16 April 2026; doi:10.1038/d41586-026-00509-9 Can you squeeze your graduate programme into a 40-hour working week?
Nature, Published online: 16 April 2026; doi:10.1038/d41586-026-01236-x Quantum machines are making inroads into biology, but have no ‘advantage’ over classical...
Nature, Published online: 16 April 2026; doi:10.1038/d41586-026-01227-y Variations in gene expression could help to explain why brain-disease risks differ accor...
Learn about the productivity tool one GitHub engineer built, and how AI supported the development process.
We’re sharing recent policy updates that developers should know about, updating our Transparency Center with the full year of 2025 data, and looking to what’s a...
Modal 是一个提供云AI算力的平台，目前提供免费的 GLM-5.1 模型到月底，但限制并发请求 1。 模型入口 直接在该页面左侧点击 Sign in 注册即可： 然后可以看到并发请求限制为 1，也就是同一时间段只能有一个连接。
现在，通过 Google 的开源应用 Google AI Edge Gallery，已经可以直接在 iPhone 和安卓手机上运行 Gemma 4 E2B、E4B 两个模型了，不消耗任何 Token，能离线使用。而且不只是对话，还支持图片、语音，甚至加入了 Skills。 不用等啦，现在就能用。
Learn how Chrome Autofill is improving support for Japanese phonetic names (Furigana), making it easier for users to fill out web forms.
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10513-8 Cytoplasmic lattices are megadalton storage complexes in mammalian oocytes
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10483-x Retraction Note: The hidden fitness of the male zebra finch courtship song
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10504-9 Editorial Expression of Concern: Creation of human tumour cells with defined genetic ele...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10519-2 Author Correction: HER2 expression identifies dynamic functional states within circulati...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10508-5 Carbonyl swapping converts cyclic ketones to saturated heterocycles
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-01241-0 Genomics-guided trial could increase options for people undergoing cancer therapy — plus...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10379-w Monolithic three-dimensional (3D) integration of tantalum pentoxide on a lithium niobate...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10362-5 Studies explaining the secondary Igk recombination mechanism are described and Cer/Sis d...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10381-2 Shelves rather than shorelines may be better topographic indicators of oceans on Earth a...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10350-9 Combined functional ultrasound imaging and Neuropixels recording of mouse brains identif...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10358-1 Analysis of 15,836 ancient West Eurasian genomes reveals hundreds of instances of direct...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10386-x This Review revisits tumour initiation and promotion in light of clonal diversity and th...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10353-6 mRNA–lipid-nanoparticle vaccines do not require type 1 conventional dendritic (cDC1) cel...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10405-x Evaluation by the Drug Rediscovery Protocol of off-label use of 37 approved cancer drugs...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10391-0 MitoCatch is a cell-type-specific mitochondrion-targeting system that links mitochondria...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10377-y A human spatial atlas of gene expression in liver based on live donors shows marked port...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10269-1 In this Perspective article, a theoretical framework for how the AP-1 family of transcri...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10384-z ThermoCas9, a genome-editing enzyme that is sensitive to the DNA methylation status of t...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10344-7 Metastasis-associated oncofetal cell states emerge at the earliest stages of colorectal...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10368-z The E3 ligase SCFFBXO42 degrades holoenzyme-free PP2Ac in complex with the coiled-coil p...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10387-w A monolithic mode-locked semiconductor laser with a continuously and widely tunable repe...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10354-5 In mice, female aggression is governed by an amygdala–to–medial hypothalamus circuit tha...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10319-8 During model distillation, large language models can subtly transmit traits unrelated to...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10392-z Scalable fabrication of ordered perovskite quantum dot superlattices enables high-effici...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10369-y This work demonstrates industrial-scale roll-to-roll fabrication of high-efficiency visi...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10324-x In situ microscopic single-particle imaging demonstrates the significance of rationally...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10367-0 PerturbFate is a high-throughput, cost-effective, single-cell platform that systematical...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10416-8 A genome-to-genome association study identifies host and viral risk factors that interac...
Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10223-1 A composable neural network emulator is described for speeding up thermoelectric generat...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-01195-3 Efforts to boost tree cover and restore degraded land globally need stable funding and t...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-00688-5 Meet the creative minds that aim to improve cancer detection and treatment.
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-00907-z An artificial-intelligence system bypasses complex equations to predict the performance...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-00690-x A breakdown of publications in the database also reveals the cancer types with the highe...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-00403-4 Through flexibility, problem-solving and the generosity of colleagues, I shepherded stud...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-00686-7 Integrated care and prevention strategies are key, but without careful planning — and su...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-01181-9 A platform for tracking the changes in gene expression and chromatin accessibility that...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-01189-1 A type of activity in the brain’s cortex, called high gamma, is widely used in studies o...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-01224-1 Using artificial-intelligence to teach other models can be cheaper and faster than build...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-00689-4 Denmark and South Korea stand out for their strong cancer strategies while England seeks...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-00691-w A description of the terminology and methodology used in this supplement, and a guide to...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-00910-4 A system of protein binders directs energy-generating organelles to targeted cells, pote...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-01248-7 Looking at a childlike version of your face might help you see childhood memories more c...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-00906-0 A large language model that is trained using AI outputs can inherit undesirable behaviou...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-01187-3 A high-resolution atlas of the healthy human liver has been assembled using gene-express...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-01102-w Grand anti-desertification schemes often fail when trees die and funding dries up — yet...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-00687-6 As some countries lower the screening age for breast, colorectal and other cancers, scie...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-01197-1 Climate-friendly technologies are the best way to stymie rising inflation — and will get...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-00911-3 If general cancer treatment fails, a tumour-type-specific therapy might be tried for oth...
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-00697-4 The models are designed to predict someone’s risk of diabetes or stroke.
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-01065-y Nothing beside remains.
Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-01204-5 Data from more than 15,000 ancient people reveal natural selection of hundreds of genes...
Learn to find and exploit real-world agentic AI vulnerabilities through five progressive challenges in this free, open source game that over 10,000 developers h...
The new Code Security Risk Assessment gives you a one-click view of vulnerabilities across your organization, at no cost. The post How exposed is your code?
Over the next several weeks, we'll release lessons on AI evals.
Affinity 是一套用于图像处理、矢量设计和排版出版的专业设计软件。在被 Canva 收购后，目前 Affinity 已完全免费开放下载、使用，并且在近日上线了中国区官网。 Affinity 整合了 Affinity Photo、Affinity Designer、Affinity Publis
著名的开源内网穿透工具 frp v0.68 更新，添加了内置存储功能，以及通过 API 操作代理功能。今后可通过 AI 来操作 frp 客户端，无需重启。 frp v0.68 frp 的这个新功能，青小蛙觉得，就是为 AI 准备的。
暂无内容。