4 papers
MedSIGHT: Towards Grounded Visual Comprehension in Medical Large Vision-Language Models
Aofei Chang, Le Huang, Alex James Boyd +4
Medical large vision-language models (Med-LVLMs) have recently achieved remarkable progress in vision-language comprehension and medical image segmentation. However, existing model…
Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization
Chenliang Li, Adel Elmahdy, Alex Boyd +7
Reinforcement learning (RL) algorithms such as PPO and GRPO are widely used to train large language models (LLMs) for multi-turn agentic tasks. However, in off-policy training pipe…
Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processes
Alex Boyd, Andrew Warrington, Taha Kass-Hout +2
Foundational marked temporal point process (MTPP) models, such as the Hawkes process, often use inexpressive model families in order to offer interpretable parameterizations of eve…
Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuning
Aofei Chang, Le Huang, Alex James Boyd +4
Medical Large Vision-Language Models (Med-LVLMs) often exhibit suboptimal attention distribution on visual inputs, leading to hallucinated or inaccurate outputs. Existing mitigatio…