arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

大厂专区

Tencent(腾讯)

2026-05-25 至 2026-05-25 共收录 6
2605.23559 2026-05-25 cs.CV cs.AI

PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide Image VQA

PathNavigate: 一种无需训练的病理学代理,具有惊喜引导扫描和共享幻灯片记忆用于全切片图像VQA

Chunze Yang, Qidong Liu, Wenjie Zhao, Yue Tang, Jiusong Ge, Di Zhang, Jiashuai Liu, Lei Wu, Junbo Lu, Ni Zhang, Xian Wu, Zeyu Gao, Chen Li

机构 * School of Comp. Science & Technology, Xi’an Jiaotong University(西安交通大学计算机科学与技术学院) Tencent Jarvis Lab(腾讯Jarvis实验室) University of Cambridge(剑桥大学)

AI总结 提出PathNavigate,一种无需训练的病理学代理,通过惊喜引导扫描和共享幻灯片记忆,在严格检查预算下高效定位证据并回答临床查询。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23522 2026-05-25 cs.LG cs.AI cs.CV

Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models

Precise: 用于流匹配模型强化学习后训练的SDE一致随机采样

Jade Zou, Tao Huang, Weijie Kong, Junzhe Li, Yue Wu, Qi Tian, Jiangfeng Xiong, Jianwei Zhang, Liefeng Bo, Zhao Zhong

机构 * Peking University(北京大学) Tencent Hunyuan(腾讯文言)

AI总结 针对流匹配模型强化学习后训练中的随机采样问题,提出Precise采样器,通过平衡探索与稳定性的SDE调度和冻结干净潜变量后验均值的近似方法,实现SDE一致性,显著提升奖励优化速度和稳定性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23320 2026-05-25 cs.AI

Human-in-the-Loop Multi-Agent Ventilator Decision Support with Contextual Bandit Preference Learning

人在回路的多智能体呼吸机决策支持与上下文赌博机偏好学习

Sijia Li, Xiaoyu Tan, Qixing Wang, Weiyi Zhao, Chen Zhan, Teqi Hao, Xuemin Wang, Lei Gu, Roland Eils, Xihe Qiu

机构 * Shanghai University of Engineering Science, Shanghai, China Tencent Youtu Lab, Tencent, China Department of Critical Care Medicine, Shanghai Tenth People's Hospital, Tongji University School of Medicine, Shanghai, China Department of Emergency Critical Disease, Songjiang Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China Max Planck Institute for Heart Lung Research, Bad Nauheim, Germany Fudan University, Shanghai, China BIH at Charit\'e -- Universit\"atsmedizin Berlin, Berlin, Germany

AI总结 提出VDSS框架,通过人在回路的多智能体协作和上下文赌博机在线偏好适应,实现呼吸机决策支持的个性化与可审计性。

Comments miccai 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23271 2026-05-25 cs.CV cs.AI

EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation

EvalVerse:面向专业电影级视频生成的流水线感知与专家校准基准测试

Songlin Yang, Haobin Zhong, Ruilin Zhang, Xiaotong Zhao, Shuai Li, Kai Zheng, Xuyi Yang, Zhe Wang, Zhenchen Tang, Yang Li, Bohai Gu, Zhengwei Peng, Yidan Huang, Mengzhou Luo, Yihang Bo, Dalu Feng, Yujia Zhang, Juntao Ma, Ruiqi Wang, Lvmin Zhang, Yuwei Guo, Frank Guan, Maneesh Agrawala, Hongbo Fu, Alan Zhao, Anyi Rao

机构 * The Hong Kong University of Science and Technology(香港科学与技术大学) Tencent(腾讯) Tsinghua University(清华大学) Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) Beijing Film Academy(北京电影学院) Stanford University(斯坦福大学) The Chinese University of Hong Kong(香港中文大学) Singapore Institute of Technology(新加坡理工学院)

AI总结 提出EvalVerse框架,通过将电影制作专业知识系统化为评估分类法、构建专家标注数据集并微调视觉语言模型进行链式推理,解决了现有基准忽视电影质量、缺乏领域特异性指标的问题,实现了对生成视频“正确性”与“优良性”的全面评估。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23191 2026-05-25 cs.LG cs.IR cs.NA math.NA

Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation

扩展更多,收缩更少:塑造有效秩动态以实现推荐中的密集扩展

Guoming Li, Shangyu Zhang, Junwei Pan, Wentao Ning, Jin Chen, Gengsheng Xue, Chao Zhou, Shudong Huang, Haijie Gu, Menglin Yang

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州)) Tencent Inc.(腾讯公司) Tencent Inc. Shenzhen China(腾讯公司深圳中国)

AI总结 针对推荐模型扩展中的嵌入坍缩问题,提出RankElastor架构,通过参数化全混合和GLU改进的P-FFN模块缓解有效秩的阻尼振荡,提升表示表达能力并实现稳健扩展。

Comments Accepted at the 32st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Research Track), KDD 2026 February Cycle

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.06684 2026-05-25 cs.CV

PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation

PixelPonder: 动态补丁自适应增强多条件文本到图像生成

Yanjie Pan, Qingdong He, Zhengkai Jiang, Pengcheng Xu, Chaoyi Wang, Jinlong Peng, Haoxuan Wang, Yun Cao, Zhenye Gan, Mingmin Chi, Bo Peng, Yabiao Wang

机构 * Fudan University(复旦大学) Tencent Youtu Lab(腾讯优图实验室) Western University(西澳大学) University of Chinese Academy of Sciences(中国科学院大学)

AI总结 提出PixelPonder统一控制框架,通过补丁级自适应条件选择和时间感知控制注入机制,解决多条件文本到图像生成中结构失真和伪影问题,在保持文本语义一致性的同时提升空间对齐精度。

详情

展开后加载摘要…

URL PDF HTML 收藏