4 papers
Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA
Kailong Fan, Anqi Pu, Yichen Wu +7
Test-time reinforcement learning adapts a model on its own unlabeled test set using majority-vote pseudo-labels and has shown strong results in mathematics. We show that this recip…
Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates
Pengfei Jin, Yiqi Tian, Kailong Fan +2
Diffusion-based inverse problem solvers can produce realistic reconstructions, but realism alone does not ensure that the recovered details are supported by the measurement. We stu…
MAPLE: Elevating Medical Reasoning from Statistical Consensus to Process-Led Alignment
Kailong Fan, Anqi Pu, Yichen Wu +7
Recent advances in medical large language models have explored Test-Time Reinforcement Learning (TTRL) to enhance reasoning. However, standard TTRL often relies on majority voting…
CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support
Yichen Wu, Kailong Fan, Sangjoon Park +9
Recent multi-agent frameworks have shown promise for oncology decision support, yet most assume centralized data access and rely on prompt-based assignment, limiting their applicab…