Cover Image

Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Che, Wang, Haozhe, Pan, Jiazhen, Wan, Zhongwei, Dai, Yong, Lin, Fangzhen, Bai, Wenjia, Rueckert, Daniel, Arcucci, Rossella
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How Far Have Medical Vision-Language Models Come? A Comprehensive Benchmarking Study
by: Liu, Che, et al.
Published: (2025)

Knowledge-enhanced Multimodal ECG Representation Learning with Arbitrary-Lead Inputs
by: Liu, Che, et al.
Published: (2025)

Utilizing Synthetic Data for Medical Vision-Language Pre-training: Bypassing the Need for Real Images
by: Liu, Che, et al.
Published: (2023)

Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement
by: Liu, Che, et al.
Published: (2024)

Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?
by: Liu, Che, et al.
Published: (2024)

How Does Diverse Interpretability of Textual Prompts Impact Medical Vision-Language Zero-Shot Tasks?
by: Wang, Sicheng, et al.
Published: (2024)

Argus: Benchmarking and Enhancing Vision-Language Models for 3D Radiology Report Generation
by: Liu, Che, et al.
Published: (2024)

G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-training
by: Liu, Che, et al.
Published: (2023)

IMITATE: Clinical Prior Guided Hierarchical Vision-Language Pre-training
by: Liu, Che, et al.
Published: (2023)

Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding
by: Li, Jun, et al.
Published: (2025)

Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions
by: Li, Jun, et al.
Published: (2025)

Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias
by: Wan, Zhongwei, et al.
Published: (2023)

Freeze the backbones: A Parameter-Efficient Contrastive Approach to Robust Medical Vision-Language Pre-training
by: Qin, Jiuming, et al.
Published: (2024)

Skill-Conditioned Gated Self-Distillation for LLM Reasoning
by: Huang, Jiazhen, et al.
Published: (2026)

Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
by: Wang, Haozhe, et al.
Published: (2025)

TorchDA: A Python package for performing data assimilation with deep learning forward and transformation functions
by: Cheng, Sibo, et al.
Published: (2024)

T3D: Advancing 3D Medical Vision-Language Pre-training by Learning Multi-View Visual Consistency
by: Liu, Che, et al.
Published: (2023)

FMBench: Benchmarking Fairness in Multimodal Large Language Models on Medical Tasks
by: Wu, Peiran, et al.
Published: (2024)

Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning
by: Wang, Haozhe, et al.
Published: (2025)

CogDoc: Towards Unified thinking in Documents
by: Xu, Qixin, et al.
Published: (2025)

MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation
by: Wan, Zhongwei, et al.
Published: (2024)

Towards Cardiac MRI Foundation Models: Comprehensive Visual-Tabular Representations for Whole-Heart Assessment and Beyond
by: Zhang, Yundi, et al.
Published: (2025)

Unsupervised whole-heart function assessment
by: Zhang, Yundi, et al.
Published: (2025)

BIMCV-R: A Landmark Dataset for 3D CT Text-Image Retrieval
by: Chen, Yinda, et al.
Published: (2024)

SuPreME: A Supervised Pre-training Framework for Multimodal ECG Representation Learning
by: Cai, Mingsheng, et al.
Published: (2025)

MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
by: Pan, Jiazhen, et al.
Published: (2025)

Multi-fidelity physics constrained neural networks for dynamical systems
by: Zhou, Hao, et al.
Published: (2024)

Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration
by: Liu, Che, et al.
Published: (2025)

Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
by: Xie, Tian, et al.
Published: (2025)

Noise2Noise Denoising of CRISM Hyperspectral Data
by: Platt, Robert, et al.
Published: (2024)

Disentangling Progress in Medical Image Registration: Beyond Trend-Driven Architectures towards Domain-Specific Strategies
by: Jian, Bailiang, et al.
Published: (2025)

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
by: Wang, Haozhe, et al.
Published: (2026)

SSR: Pushing the Limit of Spatial Intelligence with Structured Scene Reasoning
by: Zhang, Yi, et al.
Published: (2026)

Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
by: Chen, Liang, et al.
Published: (2025)

A Hybrid Machine Learning Framework for Improved Short-Term Peak-Flow Forecasting
by: Bertoli, Gabriele, et al.
Published: (2026)

Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve
by: Shen, Weixiang, et al.
Published: (2026)

Bad Seeing or Bad Thinking? Rewarding Perception for Vision-Language Reasoning
by: Wang, Haozhe, et al.
Published: (2026)

Dynamic Decision Learning: Test-Time Evolution for Abnormality Grounding in Rare Diseases
by: Li, Jun, et al.
Published: (2026)

Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth
by: Wu, Yuhuan, et al.
Published: (2026)

Language-Driven Object-Oriented Two-Stage Method for Scene Graph Anticipation
by: Zhu, Xiaomeng, et al.
Published: (2025)