This is the official implmentation of MedGround-R1, which incorporates GRPO and MedCLIP semantic reward. Without any cold start sft or cot annotation, MedGroud-R1 achieves sota on three public medical grounding benchmarks.
Official Implementation of ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs ProMed is a novel approach for enhancing medical LLMs' proactive information-seeking ability through Shapley information gain rewards and reinforcement learning frameworks toβ¦
Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learning
Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning
MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs π Paper | π€ Datasets | π€ Models Weights (Huggingface) | π€ Models Weights (ModelScope)
The main features of 545487677/molreasoner are: Scientific Tasks.
Open-source alternatives to 545487677/molreasoner include: bio-mlhui/medground-r1 β This is the official implmentation of MedGround-R1, which incorporates GRPO and MedCLIP semantic reward. Without anyβ¦ hxxding/promed β Official Implementation of ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMsβ¦ monncyann/med-u1 β Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learning. ncbi-nlp/cell-o1 β Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning. wenjielisjtu/cx-mind β CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guidedβ¦ wshi83/medagentgym β [ICLR'26] MedAgentGYM: Training LLM Agents for Code-Based Medical Reasoning at Scale.