Papers
SafeMT: Multi-turn Safety for Multimodal Language Models
Han Zhu, Juntao Dai, Jiaming Ji et al.
Towards A Scanpath-Conditioned Surprisal Theory: Modeling Reader Information States
Michael Mooney, Edmond S. L. Ho
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
Xiaoliang Fu, Jiaye Lin, Yangyi Fang et al.
Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning
Miao Li, Irina Saparina, Alexander Gurung et al.
Quantifying the Impact of Translation Errors on Multilingual LLM Evaluation
Klaudia Thellmann, Bernhard Stadler, Michael Färber et al.
Multimodal Safety Evaluation in Generative Agent Social Simulations
Alhim Adonai Vera Gonzalez, Carlos Hinojosa, Karen Sanchez et al.
Modeling Annotator Disagreement with Demographic-Aware Experts and Synthetic Perspectives
Yinuo Xu, Veronica Derricks, Allison Earl et al.
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
Junxiao Yang, Haoran Liu, Jinzhe Tu et al.
One Pair Suffices: Unlocking Universal Zero-Shot Translation via Cross-Architecture Alignment
Hao Zong, Cong Hu Yuan, Chao Bei et al.
Temporal Precision Matters: Brain-Tuning Speech Language Models with Millisecond-Resolution Neural Signals
Zhejun Zhang, Wenqing Zhou, Haozhe Xu et al.
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
Wenqi Zhang, Mengna Wang, Gangao Liu et al.
Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation
Fangda Ye, Kuicai Dong, Xie Zhifei et al.
From Competition to Synergy: Unlocking Reinforcement Learning for Subject-Driven Image Generation
Ziwei Huang, Ying Shu, Fanghao et al.
The Visual Iconicity Challenge: Evaluating Vision-Language Models on Sign Language Form–Meaning Mapping
Onur Keleş, Asli Ozyurek, Gerardo Ortega et al.
ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents
Tianjian Liu, Fanqi Wan, Jiajian Guo et al.
LLM Beliefs Are in Their Heads
Alessandro Corona Mendozza, Anders Søgaard
Beyond Static Alignment: Adaptive Arbitration for Semantic Incongruence in Semi-Supervised Multimodal Sentiment Analysis
Huicong Li, Xiangbo Ji, Wei Wu
Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain
Gang Cheng, Haibo Jin, Wenbin Zhang et al.
Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions
Dongwook Lee, Eunwoo Song, Che Hyun Lee et al.
GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing
Ming Wang, Shuang Wu, Bixuan Wang et al.
Edit-Aware Reward Modeling for Chinese Grammatical Error Correction
Yilin Li, Xiaojun Wan
FedMental: Evaluating Federated Learning for Mental Health Detection from Social Media Data
Nuredin Ali Abdelkadir, Anjali Ratnam, Zeerak Talat et al.
Amadeus: Autoregressive Model with Bidirectional Attribute Modelling for Symbolic Music
Hongju Su, Ke Li, Lan Yang et al.
Thinking in Schemas: Robust Syllogistic Reasoning in LLMs
Federico Ranaldi, Leonardo Ranaldi, Fabio Massimo Zanzotto et al.
CNSL-bench: Benchmarking the Sign Language Understanding Capabilities of MLLMs on Chinese National Sign Language
Rui Zhao, Xuewen Zhong, Xiaoyun Zheng et al.