大模型推理能力

Kwai Keye-VL 1.5 Technical Report

Biao Yang, Bin Wen, Boyang Ding, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Dunju Zang, Fan Yang, Guorui Zhou, Guowang Zhang, Han Shen, Hao Peng, Haojie Ding, Hao Wang, Haonan Fan, Hengrui Ju, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jingyun Hua, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Muhao Wei, Qiang Wang, Ruitao Wang, Sen Na, Shengnan Zhang, Siyang Mao, Sui Huang, Tianke Zhang, Tingting Gao, Wei Chen, Wei Yuan, Xiangyu Wu, Xiao Hu, Xingyu Lu, Yi-Fan Zhang, Yiping Yang, Yulong Chen, Zeyi Lu, Zhenhua Wu, Zhixin Ling, Zhuoran Yang, Ziming Li, Di Xu, Haixuan Gao, Hang Li, Jing Wang, Lejian Ren, Qigen Hu, Qianqian Wang, Shiyao Wang, Xinchen Luo, Yan Li, Yuhang Hu, Zixing Zhang

机构 * Keye Team, Kuaishou Group（快手集团Keye团队） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)

Comments Github page: https://github.com/Kwai-Keye/Keye

Towards Explainable Vulnerability Detection with Large Language Models

Qiheng Mao, Zhenhao Li, Xing Hu, Kui Liu, Xin Xia, Jianling Sun

专题命中 复杂问题求解 ：chain-of-thought(abstract)；CoT(abstract)

Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents

Tianmi Ma, Jiawei Du, Wenxin Huang, Wenjie Wang, Liang Xie, Xian Zhong, Joey Tianyi Zhou

机构 * Wuhan University of Technology（武汉理工大学） ； Agency for Science, Technology and Research, Singapore（新加坡科技研究局） ； Hubei University（湖北大学） ； University of Science and Technology of China（中国科学技术大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

ConceptBot: Enhancing Robot's Autonomy through Task Decomposition with Large Language Models and Knowledge Graph

Alessandro Leanza, Angelo Moroncelli, Giuseppe Vizzari, Francesco Braghin, Loris Roveda, Blerina Spahiu

机构 * Department of Innovative Technologies (DTI), Dalle Molle Institute for Artificial Intelligence (IDSIA), University of Applied Sciences（创新技术部门（DTI）、达摩迪人工智能研究所（IDSIA）、应用科学与艺术大学） ； Department of Mechanical Engineering, Politecnico di Milano（机械工程部门、米兰理工学院） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；planning(abstract)

Disentangling Exploration of Large Language Models by Optimal Exploitation

Tim Grams, Patrick Betz, Sascha Marton, Stefan Lüdtke, Christian Bartelt

机构 * Technical University of Clausthal（Clausthal 技术大学） ； University of Mannheim（曼海姆大学） ； University of Rostock（罗斯托克大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM using a Meta Personalized Small VLM

Sihan Yang, Huitong Ji, Shaolin Lu, Jiayi Chen, Binxiao Xu, Ming Lu, Yuanxing Zhang, Wenhui Dong, Wentao Zhang

机构 * Peking University（北京大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；CoT(abstract)

FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities

Jin Wang, Yao Lai, Aoxue Li, Shifeng Zhang, Jiacheng Sun, Ning Kang, Chengyue Wu, Zhenguo Li, Ping Luo

机构 * The University of Hong Kong（香港大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；self-correction(abstract)

Comments 37 pages, 12 figures

Small LLMs Do Not Learn a Generalizable Theory of Mind via Reinforcement Learning

Sneheel Sarangi, Hanan Salam

机构 * NYU Abu Dhabi（纽约大学阿布扎比分校） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

AKReF: An argumentative knowledge representation framework for structured argumentation

Debarati Bhattacharjee, Ashish Anand

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 20 pages, 7 figures, 2 tables

KptLLM++: Towards Generic Keypoint Comprehension with Large Language Model

Jie Yang, Wang Zeng, Sheng Jin, Lumin Xu, Wentao Liu, Chen Qian, Zhen Li, Ruimao Zhang

机构 * Sun Yat-sen University, Shenzhen（中山大学深圳校区） ； Chinese University of Hong Kong, Shenzhen（香港中文大学深圳校区） ； SenseTime Research（商汤科技研究院） ； Chinese University of Hong Kong（香港中文大学） ； Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)

Comments Extended Version of KptLLM. arXiv admin note: text overlap with arXiv:2411.01846

AssertCoder: LLM-Based Assertion Generation via Multimodal Specification Extraction

Enyuan Tian, Yiwei Ci, Qiusong Yang, Yufeng Li, Zhichao Lyu

专题命中 复杂问题求解 ：chain-of-thought(abstract)；CoT(abstract)

Comments 7 pages, 3 figures

A Systematization of Security Vulnerabilities in Computer Use Agents

Daniel Jones, Giorgio Severi, Martin Pouliot, Gary Lopez, Joris de Gruyter, Santiago Zanella-Beguelin, Justin Song, Blake Bullwinkel, Pamela Cortez, Amanda Minnich

专题命中 复杂问题求解 ：reasoning(abstract)；CoT(abstract)

Learning to Reason under Off-Policy Guidance

Jianhao Yan, Yafu Li, Zican Hu, Zhi Wang, Ganqu Cui, Xiaoye Qu, Yu Cheng, Yue Zhang

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Work in progress

From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers

Jingtong Su, Julia Kempe, Karen Ullrich

机构 * NYU（纽约大学） ； Meta AI ； FAIR 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation

Andrew Z. Wang, Songwei Ge, Tero Karras, Ming-Yu Liu, Yogesh Balaji

机构 * University of Maryland（马里兰大学） ； NVIDIA（英伟达） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments CVPR 2025

Journal ref Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), 2025, pp. 28575-28585

From Emergence to Control: Probing and Modulating Self-Reflection in Language Models

Xudong Zhu, Jiachen Jiang, Mohammad Mahdi Khalili, Zhihui Zhu

机构 * Department of Computer Science & Engineering（计算机科学与工程系） ； The Ohio State University（俄亥俄州立大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 18 pages, 9 figures

LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?

Zihan Zheng, Zerui Cheng, Zeyu Shen, Shang Zhou, Kaiyuan Liu, Hansen He, Dongruixuan Li, Stanley Wei, Hangyi Hao, Jianzhu Yao, Peiyao Sheng, Zixuan Wang, Wenhao Chai, Aleksandra Korolova, Peter Henderson, Sanjeev Arora, Pramod Viswanath, Jingbo Shang, Saining Xie

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Project Page at https://livecodebenchpro.com/

Rethinking Brain Tumor Segmentation from the Frequency Domain Perspective

Minye Shao, Zeyu Wang, Haoran Duan, Yawen Huang, Bing Zhai, Shizheng Wang, Yang Long, Yefeng Zheng

机构 * Department of Computer Science, Durham University（杜伦大学计算机科学系） ； College of Computer Science and Engineering, Dalian Minzu University（大连民族大学计算机科学与工程学院） ； Department of Automation, Tsinghua University（清华大学自动化系） ； Jarvis Research Center, Tencent YouTu Lab（腾讯YouTu实验室 Jarvis 研究中心） ； School of Computing, Northumbria University（北爱尔兰大学 computing 学院） ； SunwayAI Research Lab, Fuyang Normal University（阜阳师范学院 SunwayAI 研究实验室） ； Chinese Academy of Sciences R&D Center for Internet of Things（中国科学院物联网研究发展中心） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；planning(abstract)

Comments Accepted by IEEE Transactions on Medical Imaging

HiBerNAC: Hierarchical Brain-emulated Robotic Neural Agent Collective for Disentangling Complex Manipulation

Hongjun Wu, Heng Zhang, Pengsong Zhang, Jin Wang, Cong Wang

机构 * Johns Hopkins University（约翰霍普金斯大学） ； Italian Institute of Technology（意大利理工学院） ； University of Toronto（多伦多大学） ； Massachusetts General Hospital, Harvard University（哈佛大学麻省总医院） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；planning(abstract)

Comments 31 pages,5 figures

Paths to Causality: Finding Informative Subgraphs Within Knowledge Graphs for Knowledge-Based Causal Discovery

Yuni Susanti, Michael Färber

机构 * Fujitsu Limited（富士通有限公司） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at KDD 2025 (full research paper)

COMPKE: Complex Question Answering under Knowledge Editing

Keyuan Cheng, Zijian Kan, Zhixian He, Zhuoran Zhang, Muhammad Asif Ali, Ke Xu, Lijie Hu, Di Wang

机构 * Provable Responsible AI and Data Analytics (PRADA) Lab（可证明负责任的人工智能与数据分析实验室） ； King Abdullah University of Science and Technology（卡布斯大学） ； Peking University（北京大学） ； South China University of Technology（华南理工大学） ； Sun Yat-sen University（中山大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by ACL 2025 Findings

LLM Agents Making Agent Tools

Georg Wölflein, Dyke Ferber, Daniel Truhn, Ognjen Arandjelović, Jakob Nikolas Kather

专题命中 复杂问题求解 ：self-correction(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at ACL 2025

LatentLLM: Attention-Aware Joint Tensor Compression

Toshiaki Koike-Akino, Xiangyu Chen, Jing Liu, Ye Wang, Pu, Wang, Matthew Brand

机构 * Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 37 pages, 16 figures

MacRAG: Compress, Slice, and Scale-up for Multi-Scale Adaptive Context RAG

Woosang Lim, Zekun Li, Gyuwan Kim, Sungyoung Ji, HyeonJung Kim, Kyuri Choi, Jin Hyuk Lim, Kyungpyo Park, William Yang Wang

机构 * POSCO HOLDINGS（POSCO控股公司） ； University of California, Santa Barbara（加州大学圣巴巴拉分校） ； Google Cloud（谷歌云） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Agent Context Protocols Enhance Collective Inference

Devansh Bhardwaj, Arjun Beniwal, Shreyas Chaudhari, Ashwin Kalyan, Tanmay Rajpurohit, Karthik R. Narasimhan, Ameet Deshpande, Vishvak Murahari

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding

Sakhinana Sagar Srinivas, Akash Das, Shivam Gupta, Venkataramana Runkana

机构 * Tata Research Development（塔塔研究与发展中心） ； Design Center, Bangalore（班加罗尔设计中心） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Physics of Language Models: Part 1, Learning Hierarchical Language Structures

Zeyuan Allen-Zhu, Yuanzhi Li

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments V2 polishes writing and adds Appendix G; V3 polishes writing and changes the title; V4 improves writing and adds Appendix H (more uniform attention results)

Fleet of Agents: Coordinated Problem Solving with Large Language Models

Lars Klein, Nearchos Potamitis, Roland Aydin, Robert West, Caglar Gulcehre, Akhil Arora

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICML 2025; 28 pages, 68 figures, 8 tables

Context-aware LLM-based Safe Control Against Latent Risks

Xiyu Deng, Quan Khanh Luu, Anh Van Ho, Yorie Nakahira

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

Shang Yang, Junxian Guo, Haotian Tang, Qinghao Hu, Guangxuan Xiao, Jiaming Tang, Yujun Lin, Zhijian Liu, Yao Lu, Song Han

机构 * MIT（麻省理工学院） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by MLSys 2025. Code available at: https://github.com/mit-han-lab/omniserve