5 papers
Teach Yourself Where to Look: On-Policy Attention Self-Distillation for Reasoning
Safaeid Hossain Arib, Rabeya Akter, Ismam Nur Swapnil +3
On-policy self-distillation trains reasoning models on their own trajectories using dense token distribution guidance from a privileged teacher with access to a verified solution.…
Skip What You Can Predict: Predictive Repositioning for Policy Optimization for Efficient LLM Training
Ismam Nur Swapnil, Aranya Saha, Tanvir Ahmed Khan +3
Reinforcement learning with verifiable rewards (RLVR) can improve the reasoning ability of large language models, but repeatedly updating a policy on the same rollout batch is expe…
GRPO++: Enhancing Dermatological Reasoning under Low Resource Settings
Ismam Nur Swapnil, Aranya Saha, Tanvir Ahmed Khan +1
Vision-Language Models (VLMs) show promise in medical image analysis, yet their capacity for structured reasoning in complex domains like dermatology is often limited by data scarc…
CLARIFY: A Specialist-Generalist Framework for Accurate and Lightweight Dermatological Visual Question Answering
Aranya Saha, Tanvir Ahmed Khan, Ismam Nur Swapnil +1
Vision-language models (VLMs) have shown significant potential for medical tasks; however, their general-purpose nature can limit specialized diagnostic accuracy, and their large s…
Compression Strategies for Efficient Multimodal LLMs in Medical Contexts
Tanvir A. Khan, Aranya Saha, Ismam N. Swapnil +1
Multimodal Large Language Models (MLLMs) hold huge potential for usage in the medical domain, but their computational costs necessitate efficient compression techniques. This paper…