5 papers
Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection
Jianghao Wu, Jianfei Cai, Weiqiang Wang +3
Reinforcement learning with verifiable rewards (RLVR) can yield large reasoning gains from very few training instances, yet its strong sensitivity to which instances are used makes…
VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering
Jiayi Chen, Benteng Ma, Zehui Liao +3
While medical Multimodal Large Language Models (MLLMs) have shown promise in assisting diagnosis, they still frequently generate hallucinated responses that appear linguistically p…
EviATTA: Evidential Active Test-Time Adaptation for Medical Segment Anything Models
Jiayi Chen, Yasmeen George, Winston Chong +1
Deploying foundational medical Segment Anything Models (SAMs) via test-time adaptation (TTA) is challenging under large distribution shifts, where test-time supervision is often un…
SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization
Jianghao Wu, Yasmeen George, Jin Ye +3
Large language models (LLMs) and multimodal LLMs (MLL-Ms) excel at chain-of-thought reasoning but face distribution shift at test-time and a lack of verifiable supervision. Recent…
SAM-aware Test-time Adaptation for Universal Medical Image Segmentation
Jianghao Wu, Yicheng Wu, Yutong Xie +7
Leveraging the Segment Anything Model (SAM) for medical image segmentation remains challenging due to its limited adaptability across diverse medical domains. Although fine-tuned v…