大模型推理能力

2509.26378 2025-10-01 cs.IR cs.CV 78%

MR$^2$-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval

Junjie Zhou, Ze Liu, Lei Xiong, Jin-Ge Yao, Yueze Wang, Shitao Xiao, Fenfen Lin, Miguel Hu Chen, Zhicheng Dou, Siqi Bao, Defu Lian, Yongping Xiong, Zheng Liu

专题命中推理评测：reasoning(title,abstract)

2509.25502 2025-10-01 cs.CV 78%

Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detection

Kaiqing Lin, Zhiyuan Yan, Ruoxin Chen, Junyan Ye, Ke-Yue Zhang, Yue Zhou, Peng Jin, Bin Li, Taiping Yao, Shouhong Ding

机构 * Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Media Security, and SZU-AFS Joint Innovation Center for AI Technology（广东省智能信息处理重点实验室、深圳媒体安全重点实验室及深圳大学-AFS联合人工智能技术创新中心）； Tencent Youtu Lab（腾讯优图实验室）； Peking University（北京大学）； Sun Yat-Sen University（中山大学）

专题命中推理评测：reasoning(title,abstract)

2505.14142 2025-10-01 cs.SD eess.AS 78%

AudSemThinker: Enhancing Audio-Language Models through Reasoning over Semantics of Sound

Gijs Wijngaard, Elia Formisano, Michele Esposito, Michel Dumontier

机构 * Maastricht University（马斯特里赫特大学）

专题命中推理评测：reasoning(title,abstract)

Comments Accepted at NeurIPS 2025

2509.25281 2025-10-01 cond-mat.mtrl-sci cs.LG 70%

Mechanisms of Matter: Language Inferential Benchmark on Physicochemical Hypothesis in Materials Synthesis

Yingming Pu, Tao Lin, Hongyu Chen

机构 * Westlake University（西湖大学）

专题命中推理评测：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.LG

2507.14688 2025-10-01 cs.CL cs.AI cs.LG 67%

Mind the Gap: A Review of Arabic Post-Training Datasets and Their Limitations

Mohammed Alkhowaiter, Norah Alshahrani, Saied Alshahrani, Reem I. Masoud, Alaa Alzahrani, Deema Alnuhait, Emad A. Alghamdi, Khalid Almubarak

机构 * Refine AI ； ASAS AI ； University of Bisha（比沙大学）； University College London（伦敦大学学院）； King Salman Global Academy for Arabic（萨勒曼全球阿拉伯学院）； University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； King Abdulaziz University（阿卜杜勒阿齐兹大学）； HUMAIN

专题命中推理评测：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2509.26417 2025-10-01 cs.AI cs.LG 62%

OntoAligner Meets Knowledge Graph Embedding Aligners

Hamed Babaei Giglou, Jennifer D'Souza, Sören Auer, Mahsa Sanaei

机构 * TIB -- Leibniz Information Centre for Science and Technology（莱比锡信息科学与技术研究中心）； University of Tabriz（塔布里兹大学）

专题命中推理评测：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 10 pages of main content, 3 page references, 3 figures. Accepted to Ontology Matching Workshop at ISWC

2509.25813 2025-10-01 cs.CL cs.LG 62%

RoBiologyDataChoiceQA: A Romanian Dataset for improving Biology understanding of Large Language Models

Dragos-Dumitru Ghinea, Adela-Nicoleta Corbeanu, Adrian-Marius Dumitran

机构 * University of Bucharest（布加勒斯特大学）

专题命中推理评测：reasoning(abstract)；分类 cs.CL、cs.LG

2509.25238 2025-10-01 cs.LG cs.AI 62%

PALADIN: Self-Correcting Language Model Agents to Cure Tool-Failure Cases

Sri Vatsa Vuddanti, Aarav Shah, Satwik Kumar Chittiprolu, Tony Song, Sunishchal Dev, Kevin Zhu, Maheep Chaudhary

专题命中推理评测：reasoning(abstract)；分类 cs.AI、cs.LG

2509.24297 2025-10-01 cs.CL cs.AI 62%

Q-Mirror: Unlocking the Multi-Modal Potential of Scientific Text-Only QA Pairs

Junying Wang, Zicheng Zhang, Ye Shen, Yalun Wu, Yingji Liang, Yijin Guo, Farong Wen, Wenzhe Li, Xuezhi Zhao, Qi Jia, Guangtao Zhai

机构 * Fudan University（复旦大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Shanghai Jiao Tong University（上海交通大学）

专题命中推理评测：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 25 pages

2507.14017 2025-10-01 cs.CL cs.LG 62%

Efficient Temporal Tokenization for Mobility Prediction with Large Language Models

Haoyu He, Haozheng Luo, Yan Chen, Qi R. Wang

机构 * Northeastern University, Boston, MA（东北大学）； Northwestern University, Evanston, IL（西北大学）

专题命中推理评测：reasoning(abstract)；分类 cs.CL、cs.LG

Journal ref Proceedings of the 3rd Workshop on Efficient Systems for Foundation Models (ES-FoMo III) at ICML 2025

2505.21500 2025-10-01 cs.CV cs.AI cs.CL 62%

ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models

Dingming Li, Hongxing Li, Zixuan Wang, Yuchen Yan, Hang Zhang, Siqi Chen, Guiyang Hou, Shengpei Jiang, Wenqi Zhang, Yongliang Shen, Weiming Lu, Yueting Zhuang

机构 * Zhejiang University（浙江大学）； University of Electronic Science and Technology of China（电子科技大学）； The Chinese University of Hong Kong（香港中文大学）

专题命中推理评测：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Project: https://zju-real.github.io/ViewSpatial-Page/

2509.26225 2025-10-01 cs.CV cs.AI 57%

An Experimental Study on Generating Plausible Textual Explanations for Video Summarization

Thomas Eleftheriadis, Evlampios Apostolidis, Vasileios Mezaris

机构 * IEEE CBMI 2025

专题命中推理评测：reasoning(abstract)；分类 cs.AI

Comments IEEE CBMI 2025. This is the authors' accepted version. The final publication is available at https://ieeexplore.ieee.org/

2509.25229 2025-10-01 cs.AI 57%

Blueprint-Bench: Comparing spatial intelligence of LLMs, agents and image models

Lukas Petersson, Axel Backlund, Axel Wennstöm, Hanna Petersson, Callum Sharrock, Arash Dabiri

机构 * Andon Labs（安登实验室）

专题命中推理评测：reasoning(abstract)；分类 cs.AI

Comments 9 pages, 8 figures, submitted for ICLR 2026

2507.04909 2025-10-01 cs.CV cs.AI 57%

HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding

Yuxuan Cai, Jiangning Zhang, Zhenye Gan, Qingdong He, Xiaobin Hu, Junwei Zhu, Yabiao Wang, Chengjie Wang, Zhucun Xue, Chaoyou Fu, Xinwei He, Xiang Bai

机构 * Fantasyele

专题命中推理评测：reasoning(abstract)；分类 cs.AI

Comments Under review

2509.26047 2025-10-01 cs.CV 50%

DGM4+: Dataset Extension for Global Scene Inconsistency

Gagandeep Singh, Samudi Amarsinghe, Priyanka Singh, Xue Li

专题命中推理评测：reasoning(abstract)

Comments 8 pages, 3 figures

2509.25654 2025-10-01 cs.CV 50%

DescribeEarth: Describe Anything for Remote Sensing Images

Kaiyu Li, Zixuan Jiang, Xiangyong Cao, Jiayu Wang, Yuchen Xiao, Deyu Meng, Zhi Wang

机构 * School of Software Engineering, Xi’an Jiaotong University（西安交通大学软件工程学院）； College of Artificial Intelligence, Xi’an Jiaotong University（西安交通大学人工智能学院）； School of Computer Science and Technology and Ministry of Education Key Lab For Intelligent Networks and Network Security, Xi’an Jiaotong University（西安交通大学计算机科学与技术学院和教育部智能网络与网络安全重点实验室）； School of Mathematics and Statistics and Ministry of Education Key Lab of Intelligent Networks and Network Security, Xi’an Jiaotong University（西安交通大学数学与统计学院和教育部智能网络与网络安全重点实验室）； Pazhou Laboratory (Huangpu), Guangzhou, Guangdong, China（琶洲实验室（黄埔），广州，广东，中国）

专题命中推理评测：planning(abstract)

2507.15849 2025-10-01 cs.CL cs.AI cs.LG 82%

The Impact of Language Mixing on Bilingual LLM Reasoning

Yihao Li, Jiayi Xin, Miranda Muqing Miao, Qi Long, Lyle Ungar

机构 * University of Pennsylvania（宾夕法尼亚大学）

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

Comments Accepted at EMNLP 2025 (Main Conference)

2509.25243 2025-10-01 cs.SE cs.AI 77%

Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation

Xunzhu Tang, Iyiola Emmanuel Olatunji, Tiezhu Sun, Jacques Klein, Tegawende F. Bissyande

机构 * University of Luxembourg（卢森堡大学）

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

2505.15865 2025-10-01 cs.CV 67%

How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads

Ingeol Baek, Hwan Chang, Sunghyun Ryu, Hwanhee Lee

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)

Comments EMNLP 2025 Oral

2509.26507 2025-10-01 cs.NE cs.AI cs.LG stat.ML 62%

The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain

Adrian Kosowski, Przemysław Uznański, Jan Chorowski, Zuzanna Stamirowska, Michał Bartoszkiewicz

机构 * Pathway

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

Comments Code available at: https://github.com/pathwaycom/bdh Accompanying blog: https://pathway.com/research/bdh

2509.25591 2025-10-01 cs.AI cs.CL q-bio.OT 62%

Building the EHR Foundation Model via Next Event Prediction

Zekai Chen, Arda Pekis, Kevin Brown

机构 * Standard Model Biomedicine（标准模型生物医学）

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

2508.19294 2025-10-01 cs.CV cs.AI cs.CL 62%

Object Detection with Multimodal Large Vision-Language Models: An In-depth Review

Ranjan Sapkota, Manoj Karkee

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

Comments First Peer Reviewed Review Paper for Object Detection with Vision-Language Models (VLMs)

Journal ref Information Fusion, 2025

2509.26114 2025-10-01 cs.LG 57%

Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models

Jaesung R. Park, Junsu Kim, Gyeongman Kim, Jinyoung Jo, Sean Choi, Jaewoong Cho, Ernest K. Ryu

机构 * Department of Mathematics, UCLA（UCLA数学系）； Department of Mathematical Sciences, Seoul National University（首尔国立大学数学科学系）； KRAFTON ； Department of Linguistics, Stanford University（斯坦福大学语言学系）； Department of Computer Science and Engineering, Santa Clara University（圣克拉拉大学计算机科学与工程系）

专题命中其他推理：reasoning(abstract)；分类 cs.LG

2509.25525 2025-10-01 cs.CR cs.LG 57%

Defeating Cerberus: Concept-Guided Privacy-Leakage Mitigation in Multimodal Language Models

Boyang Zhang, Istemi Ekin Akkus, Ruichuan Chen, Alice Dethise, Klaus Satzke, Ivica Rimac, Yang Zhang

机构 * CISPA Helmholtz Center for Information Security（CISPA赫尔姆霍茨信息安全中心）； Nokia Bell Labs（诺基亚贝尔实验室）

专题命中其他推理：reasoning(abstract)；分类 cs.LG

2505.23416 2025-10-01 cs.DB cs.LG 57%

KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction

Jang-Hyun Kim, Jinuk Kim, Sangwoo Kwon, Jae W. Lee, Sangdoo Yun, Hyun Oh Song

专题命中其他推理：reasoning(abstract)；分类 cs.LG

Comments NeurIPS 2025 Oral. Code: https://github.com/snu-mllab/KVzip

2509.26330 2025-10-01 cs.CV cs.IR 50%

SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image Retrieval

Ren-Di Wu, Yu-Yen Lin, Huei-Fang Yang

机构 * National Sun Yat-sen University（国立中山大学）

专题命中其他推理：reasoning(abstract)

Comments 20 pages, 9 figures

2509.26012 2025-10-01 cs.CV 50%

SETR: A Two-Stage Semantic-Enhanced Framework for Zero-Shot Composed Image Retrieval

Yuqi Xiao, Yingying Zhu

机构 * Yuqi Xiao, Yingying Zhu

专题命中其他推理：reasoning(abstract)

1. 推理评测 25 篇

MR$^2$-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval

Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detection

AudSemThinker: Enhancing Audio-Language Models through Reasoning over Semantics of Sound

Mechanisms of Matter: Language Inferential Benchmark on Physicochemical Hypothesis in Materials Synthesis

Mind the Gap: A Review of Arabic Post-Training Datasets and Their Limitations

OntoAligner Meets Knowledge Graph Embedding Aligners

RoBiologyDataChoiceQA: A Romanian Dataset for improving Biology understanding of Large Language Models

PALADIN: Self-Correcting Language Model Agents to Cure Tool-Failure Cases

Q-Mirror: Unlocking the Multi-Modal Potential of Scientific Text-Only QA Pairs

Efficient Temporal Tokenization for Mobility Prediction with Large Language Models

ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models

An Experimental Study on Generating Plausible Textual Explanations for Video Summarization

Blueprint-Bench: Comparing spatial intelligence of LLMs, agents and image models

HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding

DGM4+: Dataset Extension for Global Scene Inconsistency

DescribeEarth: Describe Anything for Remote Sensing Images

2. 其他推理 11 篇

The Impact of Language Mixing on Bilingual LLM Reasoning

Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation

How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads

The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain

Building the EHR Foundation Model via Next Event Prediction

Object Detection with Multimodal Large Vision-Language Models: An In-depth Review

Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models

Defeating Cerberus: Concept-Guided Privacy-Leakage Mitigation in Multimodal Language Models

KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction

SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image Retrieval

SETR: A Two-Stage Semantic-Enhanced Framework for Zero-Shot Composed Image Retrieval