From Reward Signal to Visual Utility: A Controlled Audit of Medical VLM Post-Training
cs.CV, cs.AI
Submitted: 2026-09-25
Updated: 2026-09-25
Terminology
Sources
- Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning
- LoRA: Low-Rank Adaptation of Large Language Models
- SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Perception-Aware Policy Optimization for Multimodal Reasoning
- Do Medical Vision Language Models Actually See? A Counterfactual Grounding Framework and Hard-Negative Contrastive Training for Visually-Reliant Medical VLMs
- Beyond Accuracy: Evaluating Visual Grounding In Multimodal Medical Reasoning
- PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models