# MedLoc-R1: Performance-Aware Curriculum Reward Scheduling for GRPO-Based Medical Visual Grounding

arXiv: https://arxiv.org/abs/2603.28120 · HTML: https://mlsanity.com/paper/2603.28120/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Human-level performance in first-person multiplayer games with population-based deep reinforcement learning](https://mlsanity.com/paper/1807.01281/) (2018)
- [Reverse Curriculum Generation for Reinforcement Learning](https://mlsanity.com/paper/1707.05300/) (2017)
- [Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models](https://mlsanity.com/paper/2503.13939/) (2025)
- [Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study](https://mlsanity.com/paper/2209.15517/) (2022)
- [Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration](https://mlsanity.com/paper/2202.04628/) (2022)
- [One RL to See Them All: Visual Triple Unified Reinforcement Learning](https://mlsanity.com/paper/2505.18129/) (2025)
- [VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning](https://mlsanity.com/paper/2507.22607/) (2025)
- [BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning](https://mlsanity.com/paper/1806.06161/) (2018)
- [MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization](https://mlsanity.com/paper/2507.02994/) (2025)
- [Improving Medical Reasoning with Curriculum-Aware Reinforcement Learning](https://mlsanity.com/paper/2505.19213/) (2025)
- [TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation](https://mlsanity.com/paper/2503.04872/) (2025)
- [Style Curriculum Learning for Robust Medical Image Segmentation](https://mlsanity.com/paper/2108.00402/) (2021)
- [Curriculum Prompting Foundation Models for Medical Image Segmentation](https://mlsanity.com/paper/2409.00695/) (2024)
- [Prompt as Knowledge Bank: Boost Vision-language model via Structural Representation for zero-shot medical detection](https://mlsanity.com/paper/2502.16223/) (2025)
- [iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detection](https://mlsanity.com/paper/2506.00406/) (2025)

## Abstract (arXiv)

Medical visual grounding serves as a crucial foundation for fine-grained multimodal reasoning and interpretable clinical decision support. Despite recent advances in reinforcement learning (RL) for grounding tasks, existing approaches such as Group Relative Policy Optimization~(GRPO) suffer from severe reward sparsity when directly applied to medical images, primarily due to the inherent difficulty of localizing small or ambiguous regions of interest, which is further exacerbated by the rigid and suboptimal nature of fixed IoU-based reward schemes in RL. This leads to vanishing policy gradients and stagnated optimization, particularly during early training. To address this challenge, we propose MedLoc-R1, a performance-aware reward scheduling framework that progressively tightens the reward criterion in accordance with model readiness. MedLoc-R1 introduces a sliding-window performance tracker and a multi-condition update rule that automatically adjust the reward schedule from dense, easily obtainable signals to stricter, fine-grained localization requirements, while preserving the favorable properties of GRPO without introducing auxiliary networks or additional gradient paths. Experiments on three medical visual grounding benchmarks demonstrate that MedLoc-R1 consistently improves both localization accuracy and training stability over GRPO-based baselines. Our framework offers a general, lightweight, and effective solution for RL-based grounding in high-stakes medical applications. Code & checkpoints are available at hyperlinkhttps://github.com/MembrAI/MedLoc-R1.