5 papers
Video-Based Reward Modeling for Computer-Use Agents
Linxin Song, Jieyu Zhang, Huanxin Sheng +6
Computer-using agents (CUAs) are becoming increasingly capable; however, it remains difficult to scale evaluation of whether a trajectory truly fulfills a user instruction. In this…
MED-COPILOT: A Medical Assistant Powered by GraphRAG and Similar Patient Case Retrieval
Shuheng Chen, Namratha Patil, Haonan Pan +4
Clinical decision-making requires synthesizing heterogeneous evidence, including patient histories, clinical guidelines, and trajectories of comparable cases. While large language…
Experiential Reinforcement Learning
Taiwei Shi, Sihao Chen, Bowen Jiang +3
Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually…
The Hallucination Tax of Reinforcement Finetuning
Linxin Song, Taiwei Shi, Jieyu Zhao
Reinforcement finetuning (RFT) has become a standard approach for enhancing the reasoning capabilities of large language models (LLMs). However, its impact on model trustworthiness…
Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation
Yijun Pan, Taiwei Shi, Jieyu Zhao +1
Large language models (LLMs) are highly sensitive to even small amounts of unsafe training data, making effective detection and filtering essential for trustworthy model developmen…