Papers
Black-Box Membership Inference Attacks for Video Training Data in Multimodal Large Language Models
Jinrui Wang, Zhenfeng Gao, Wendan Wang et al.
BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
Rui Miao, Yixin Liu, Yili Wang et al.
False Friends or Cognates? A Cross-lingual Semantic Ambiguity Evaluation for Galician, Portuguese and Spanish
Marta Vázquez Abuín, Jose Camacho-Collados, Marcos Garcia
Towards Fast and Accurate Modeling for Cross-Lingual Label Projection
Thang Le, Huy Huu Nguyen, Anh Tuan Luu et al.
Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment
Woody Haosheng Gan, William Barr Held, Diyi Yang
HowToNarrate: A General-Domain Benchmark for Synchronized Video Narration with External Knowledge
Xueyan Wang, Dingyi Yang, Qin Jin
Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue
Thomas P. Utting, Mario Giulianelli, Arabella Sinclair
EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding
Pengze Guo, Jingxi Liang, Zhiwen Xie et al.
From Where Words Come: Efficient Regularization of Code Tokenizers Through Source Attribution
Pavel Chizhov, Egor Bogomolov, Ivan P. Yamshchikov
REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache Compression
Mengjie Li, Yuan Feng, Xike Xie et al.
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression
Chengzhengxu Li, Xiaoming Liu, Zhaohan Zhang et al.
Polymorphic Universal Transformer
Yilong Chen, Zitian Gao, Yihao Xiao et al.
Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models
Dan Shi, Zhuowen Han, Simon Ostermann et al.
One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement
Yixiao Zhou, Dongzhou Cheng, Zhiliang wu et al.
Discovering a Shared Logical Subspace: Steering LLM Logical Reasoning via Alignment of Natural-Language and Symbolic Views
Feihao Fang, My T. Thai, Yuanyuan Lei
Fast and Accurate Fisher-Guided Quantization via Efficient Kronecker Factorization
Viktoriia A. Chekalina, Gerasin Timofey, Andrey Kuznetsov et al.
MemCoRL: Alternating Co-Optimization of Memory Retrieval and Utilization via Collaborative Reinforcement Learning
Yuewen Liu, Peng Xu, Muxi Diao et al.
More Aligned, Less Diverse? Analyzing the Grammar and Lexicon of Two Generations of LLMs
Adrián Gude, Roi Santos-Rios, Francis Bond et al.
S^4: Operationalizing Speech Act Theory for Strategic Semi-Structured Psychiatric Interview
Guanqun Bi, Zhoufu Liu, Zhuang Chen et al.
Uncertainty-Aware Routing for Principled Alignment with MoE Dynamics
Yilong Chen, Junyuan Shang, Yuchen Feng et al.
JoPR: Joint Emotion Perception and Reasoning for Conversational Emotion Recognition
Yumeng Fu, Weitao Huang, Junjie Wu et al.
BEFT: Bias-Efficient Fine-Tuning of Language Models in Low-Data Regimes
Baichuan Huang, Ananth Balashankar, Amir Aminifar
ReTraceQA: Evaluating Reasoning Traces of Small Language Models in Commonsense Question Answering
Francesco Maria Molfese, Luca Moroni, Ciro Porcaro et al.
HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models
Feiyu Zhao, Yiming Chen, Wenhuan Lu et al.
ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following
Yuancheng Yang, Lin Yang, Xu Wang et al.