Papers
SpeakerSleuth: Can Large Audio-Language Models Judge Speaker Consistency across Multi-turn Dialogues?
Jonggeun Lee, Junseong Pyo, Gyuhyeon Seo et al.
Aligned Multi-View Scripts for Universal Chart-to-Code Generation
Zhihan Zhang, Lizi Liao
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora
Jiaxin Bai, Wei Fan, Qi Hu et al.
Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval
Hao Xu, Rite Bo, Fausto Giunchiglia et al.
ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation
Gibson Nkhata, Uttamasha Anjally Oyshi, Quan Mai et al.
R^3AG: Retriever Routing for Retrieval-Augmented Generation
Tong Zhao, Yutao Zhu, Yucheng Tian et al.
AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation
Rui Qian, Chuanhang Deng, Qiang Huang et al.
HSCodeComp: A Realistic and Expert-level Agent Benchmark for Hierarchical Rule Application
Tian Lan, Yiqian Yang, Qianghuai Jia et al.
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
Zhexin Zhang, Xian Qi Loye, Victor Shea-Jay Huang et al.
THOR: A Theta-Gamma Hierarchical Oscillatory Reasoning Framework for Multi-hop QA
Ziyang Ling, Ronald X. Xu, Mingzhai Sun
Beyond the Last Frame: Process-aware Evaluation for Generative Video Reasoning
Yifan Li, YuKai Gu, Yingqian Min et al.
Bridging Internal Consistency and External Alignment: A Causal and Dynamic Interpretability Framework for LLM Generation
Shuyao Xiao, Shengling Wang, Ke Chao
Beyond Ranking: Fine-Grained Diagnostics and Self-Improvement for MLLMs
Mingze Xu, Zijing Zhao, Qiming Peng et al.
ReEfBench: Quantifying the Reasoning Efficiency of LLMs
Zhizhang Fu, Yuancheng Gu, Chenkai Hu et al.
Zero-Shot Multimodal Retrieval with Multi-Scale Contextual Representations
Sourajit Saha, Tejas Gokhale
Uncovering Sentiment Analysis Circuit in Large Language Model
Shichen Li, Zhouyang Wang, Zhongqing Wang et al.
PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling
Ai Jian, Jingqing Ruan, Xing Ma et al.
SPENCE: A Syntactic Probe for Detecting Contamination in NL2SQL Benchmarks
Mohammadtaher Safarzadeh, Hitesh Laxmichand Patel, Afshin Oroojlooy et al.
The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs
Zihan Chen, Yiming Zhang, Wenxiang Geng et al.
Leibniz: Theory-of-Mind Driven Neuro-Symbolic Logical Reasoning via Multi-Agent Collaboration
Yue Fan, Hu Zhang, Yunxiao Zhao et al.
RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora
Hanjun Cho, Jay-Yoon Lee
League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models
Qianhong Guo, Wei Xie, Xiaofang Cai et al.
Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention
Zhen Yang, Mingyang Zhang, Feng Chen et al.
Backdoor Collapse: Eliminating Unknown Threats Via Known Backdoor Aggregation In Language Models
Liang Lin, Miao Yu, Moayad Aloqaily et al.