大模型推理能力

Kimi K2: Open Agentic Intelligence

Kimi K2：开放代理智能

Kimi Team, Yifan Bai, Yiping Bao, Y. Charles, Cheng Chen, Guanduo Chen, Haiting Chen, Huarong Chen, Jiahao Chen, Ningxin Chen, Ruijue Chen, Yanru Chen, Yuankun Chen, Yutian Chen, Zhuofu Chen, Jialei Cui, Hao Ding, Mengnan Dong, Angang Du, Chenzhuang Du, Dikang Du, Yulun Du, Yu Fan, Yichen Feng, Kelin Fu, Bofei Gao, Chenxiao Gao, Hongcheng Gao, Peizhong Gao, Tong Gao, Yuyao Ge, Shangyi Geng, Qizheng Gu, Xinran Gu, Longyu Guan, Haiqing Guo, Jianhang Guo, Xiaoru Hao, Tianhong He, Weiran He, Wenyang He, Yunjia He, Chao Hong, Hao Hu, Yangyang Hu, Zhenxing Hu, Weixiao Huang, Zhiqi Huang, Zihao Huang, Tao Jiang, Zhejun Jiang, Xinyi Jin, Yongsheng Kang, Guokun Lai, Cheng Li, Fang Li, Haoyang Li, Ming Li, Wentao Li, Yang Li, Yanhao Li, Yiwei Li, Zhaowei Li, Zheming Li, Hongzhan Lin, Xiaohan Lin, Zongyu Lin, Chengyin Liu, Chenyu Liu, Hongzhang Liu, Jingyuan Liu, Junqi Liu, Liang Liu, Shaowei Liu, T. Y. Liu, Tianwei Liu, Weizhou Liu, Yangyang Liu, Yibo Liu, Yiping Liu, Yue Liu, Zhengying Liu, Enzhe Lu, Haoyu Lu, Lijun Lu, Yashuo Luo, Shengling Ma, Xinyu Ma, Yingwei Ma, Shaoguang Mao, Jie Mei, Xin Men, Yibo Miao, Siyuan Pan, Yebo Peng, Ruoyu Qin, Zeyu Qin, Bowen Qu, Zeyu Shang, Lidong Shi, Shengyuan Shi, Feifan Song, Jianlin Su, Zhengyuan Su, Lin Sui, Xinjie Sun, Flood Sung, Yunpeng Tai, Heyi Tang, Jiawen Tao, Qifeng Teng, Chaoran Tian, Chensi Wang, Dinglu Wang, Feng Wang, Hailong Wang, Haiming Wang, Jianzhou Wang, Jiaxing Wang, Jinhong Wang, Shengjie Wang, Shuyi Wang, Si Wang, Xinyuan Wang, Yao Wang, Yejie Wang, Yiqin Wang, Yuxin Wang, Yuzhi Wang, Zhaoji Wang, Zhengtao Wang, Zhengtao Wang, Zhexu Wang, Chu Wei, Qianqian Wei, Haoning Wu, Wenhao Wu, Xingzhe Wu, Yuxin Wu, Chenjun Xiao, Jin Xie, Xiaotong Xie, Weimin Xiong, Boyu Xu, Jinjing Xu, L. H. Xu, Lin Xu, Suting Xu, Weixin Xu, Xinran Xu, Yangchuan Xu, Ziyao Xu, Jing Xu, Jing Xu, Junjie Yan, Yuzi Yan, Hao Yang, Xiaofei Yang, Yi Yang, Ying Yang, Zhen Yang, Zhilin Yang, Zonghan Yang, Haotian Yao, Xingcheng Yao, Wenjie Ye, Zhuorui Ye, Bohong Yin, Longhui Yu, Enming Yuan, Hongbang Yuan, Mengjie Yuan, Siyu Yuan, Haobing Zhan, Dehao Zhang, Hao Zhang, Wanlu Zhang, Xiaobin Zhang, Yadong Zhang, Yangkun Zhang, Yichi Zhang, Yizhi Zhang, Yongting Zhang, Yu Zhang, Yutao Zhang, Yutong Zhang, Zheng Zhang, Haotian Zhao, Yikai Zhao, Zijia Zhao, Huabin Zheng, Shaojie Zheng, Longguang Zhong, Jianren Zhou, Xinyu Zhou, Zaida Zhou, Jinguo Zhu, Zhen Zhu, Weiyu Zhuang, Xinxing Zu

机构 * Kimi Team（Kimi 团队） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 Kimi K2是一款开源大语言模型，通过混合专家架构和MuonClip优化器实现先进代理能力，表现优于现有非思考模型。

Comments tech report of Kimi K2, with minor updates

UniGeM: Unifying Data Mixing and Selection via Geometric Exploration and Mining

UniGeM: 通过几何探索与挖掘统一数据混合与选择

Changhao Wang, Yunfei Yu, Xinhao Yao, Jiaolong Yang, Riccardo Cantoro, Chaobo Li, Qing Cui, Jun Zhou

机构 * Politecnico di Torino（托斯大学） ； Ant Group（蚂蚁集团） ； Renmin University of China（中国人民大学） ； Institute of Microelectronics of the CAS（中国科学院微电子研究所） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

AI总结 UniGeM通过几何探索与挖掘统一数据混合与选择，提升大语言模型的数据效率和推理性能

A Multi-scale Linear-time Encoder for Whole-Slide Image Analysis

全滑动图像分析的多尺度线性时间编码器

Jagan Mohan Reddy Dwarampudi, Joshua Wong, Hien Van Nguyen, Tania Banerjee

机构 * Department of Electrical and Computer Engineering, University of Houston（电子与计算机工程系，休斯顿大学） ； Department of Information Science Technology, University of Houston（信息科学与技术系，休斯顿大学） ； Department of Neurology, College of Medicine, University of Florida（神经病学系，医学学院，佛罗里达大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

AI总结 MARBLE是一种基于Mamba的多尺度线性时间编码器，通过并行处理和线性时间建模，实现高效且可扩展的全滑动图像分析。

Comments Accepted to ISBI 2026, 4 pages with 2 figures

Test-time Recursive Thinking: Self-Improvement without External Feedback

测试时递归思考：无需外部反馈的自我提升

Yufan Zhuang, Chandan Singh, Liyuan Liu, Yelong Shen, Dinghuai Zhang, Jingbo Shang, Jianfeng Gao, Weizhu Chen

机构 * Microsoft Research（微软研究院） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL

AI总结 本文提出 TRT 框架，使 LLM 在无需外部反馈的情况下实现自我提升，开源模型在 AIME-25/24 上达到 100% 准确率，闭源模型在 LiveCodeBench 最难问题上提升 10.4-14.8 个百分点。

UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval

UniFGVC: 一种通用无训练少样本细粒度视觉分类方法通过属性感知多模态检索

Hongyu Guo, Xiangzhao Hao, Jiarui Guo, Haiyun Guo, Jinqiao Wang, Tat-Seng Chua

机构 * School of Traffic and Transportation, Beijing Jiaotong University（交通与运输学院，北京交通大学） ； Foundation Modal Research Center, Institute of Automation, Chinese Academy of Sciences（基础模态研究中心，自动化研究所） ； Queen Mary School Hainan, Beijing University of Posts and Telecommunications（海南女王学院，北京邮电大学） ； Department of Computer Science, NUS School of Computing（计算机科学系，国立大学计算机学院） 纠错

专题命中 其他推理 ：chain-of-thought(abstract)；分类 cs.AI

AI总结 UniFGVC通过属性感知多模态检索方法，实现无训练少样本细粒度视觉分类，优于现有方法。

TRACE: Temporal Radiology with Anatomical Change Explanation for Grounded X-ray Report Generation

TRACE: 基于解剖变化解释的时序放射学用于 grounded X-ray 报告生成

OFM Riaz Rahman Aranya, Kevin Desai

机构 * The University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校） 纠错

专题命中 其他推理 ：reasoning(abstract)

AI总结 TRACE 是首个结合时序比较、变化分类和空间定位的模型，通过边界框坐标实现对胸片变化的自然语言描述，提升放射学报告生成的准确性与可靠性。