GRPO++: Enhancing Dermatological Reasoning under Low Resource Settings

• URL: http://arxiv.org/abs/2510.01236v1
• Date: Tue, 23 Sep 2025 18:32:08 GMT
• Title: GRPO++: Enhancing Dermatological Reasoning under Low Resource Settings
• Abstract summary: We introduce DermIQ-VLM, a VLM developed through a multi-stage, resource-efficient methodology to emulate a dermatologist's diagnostic process.<n>Our primary contribution is a modified version of Grouped Relative Policy Optimization ( GRPO), called GRPO++, which stabilizes the powerful but data-intensive GRPO framework.<n>A preliminary evaluation on a curated dermatological dataset demonstrates that our proposed methodology yields notable performance gains over standard fine-tuning approaches.
• Score: 0.5310914438304387
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Vision-Language Models (VLMs) show promise in medical image analysis, yet their capacity for structured reasoning in complex domains like dermatology is often limited by data scarcity and the high computational cost of advanced training techniques. To address these challenges, we introduce DermIQ-VLM, a VLM developed through a multi-stage, resource-efficient methodology designed to emulate a dermatologist's diagnostic process. Our primary contribution is a modified version of Grouped Relative Policy Optimization (GRPO), called GRPO++, which stabilizes the powerful but data-intensive GRPO framework. Our proposed training pipeline first employs GRPO++ for reasoning-oriented disease recognition, followed by supervised fine-tuning for conversational ability. To mitigate factual errors introduced during this step, we then align the model using Direct Preference Optimization (DPO), leveraging a Knowledge Graph-based system as a scalable proxy for expert preference. A preliminary evaluation on a curated dermatological dataset demonstrates that our proposed methodology yields notable performance gains over standard fine-tuning approaches. These findings validate the potential of our pipeline as a feasible pathway for developing specialized, reliable VLMs in resource-constrained environments.

Related papers

• AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO [78.36537400975298]
  Group Relative Policy Optimization (GRPO) has demonstrated remarkable success in aligning text-to-image (T2I) flow models with human preferences.<n>We have identified that the learning loop of current flow-based GRPO is fundamentally decoupled from the learner's current capability.<n>We propose Adaptive GRPO (AdaGRPO), a novel capability-aware RL algorithm tailored for flow models.
  arXiv  Detail & Related papers  (2026-06-05T02:07:08Z)
• V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think [90.69263509098948]
  We introduce Variational GRPO, a method that integrates ELBO-based surrogates with the Group Relative Policy Optimization algorithm.<n>V-GRPO achieves state-of-the-art performance in text-to-image synthesis, while delivering a $2times$ speedup over MixGRPO and a $3times$ speedup over DiffusionNFT.
  arXiv  Detail & Related papers  (2026-04-25T17:03:21Z)
• A Systematic Approach for Large Language Models Debugging [9.144050771609637]
  Large language models (LLMs) have become central to modern AI, powering applications from open-ended text generation to complex agent-based reasoning.<n>This paper introduces a systematic approach for LLM debug that treats models as observable systems.<n>By unifying evaluation, interpretability, and error-analysis practices, our approach enables practitioners to iteratively diagnose model weaknesses.
  arXiv  Detail & Related papers  (2026-04-24T21:30:33Z)
• Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models [65.4947731385794]
  We present a unified multi-agent visual reasoning framework that evolves from our foundational image-centric model, Insight-V.<n>We introduce two novel algorithms, ST-GRPO and J-GRPO, which enhance spatial-temporal reasoning and improve evaluative robustness.<n>Experiments on base models like LLaVA-NeXT and Qwen2.5-VL demonstrate significant performance gains across challenging image and video reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-03-18T15:28:07Z)
• TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization [97.18886232580131]
  Large language models have demonstrated strong reasoning capabilities in complex tasks through tool integration.<n>We propose Turn-Level GRPO, a lightweight RL algorithm that performs turn-level group sampling for fine-grained optimization.
  arXiv  Detail & Related papers  (2026-01-23T06:21:33Z)
• BotaCLIP: Contrastive Learning for Botany-Aware Representation of Earth Observation Data [5.63123057685834]
  BotaCLIP is a lightweight framework for adapting a pre-trained foundation model to inject domain-specific knowledge.<n>We show how BotaCLIP can inject expert knowledge into data-scarce settings, enabling frugal representation learning.
  arXiv  Detail & Related papers  (2025-11-26T09:19:06Z)
• MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning [52.064286116035134]
  We develop MedAlign, a framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA)<n>We first propose a multimodal Direct Preference Optimization (mDPO) objective to align preference learning with visual context.<n>We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM.
  arXiv  Detail & Related papers  (2025-10-24T02:11:05Z)
• An Agentic Model Context Protocol Framework for Medical Concept Standardization [5.12407270785129]
  We develop a zero-training, hallucination-preventive mapping system based on the Model Context Protocol (MCP)<n>The system enables explainable mapping and significantly improves efficiency and accuracy with minimal effort.
  arXiv  Detail & Related papers  (2025-09-04T02:32:22Z)
• A Survey of Direct Preference Optimization [103.59317151002693]
  Large Language Models (LLMs) have demonstrated unprecedented generative capabilities.<n>Their alignment with human values remains critical for ensuring helpful and harmless deployments.<n>Direct Preference Optimization (DPO) has recently gained prominence as a streamlined alternative.
  arXiv  Detail & Related papers  (2025-03-12T08:45:15Z)
• Large Language Models are Powerful Electronic Health Record Encoders [4.520903886487343]
  General-purpose Large Language Models (LLMs) are used to encode EHR data into representations for downstream clinical prediction tasks.<n>We show that LLM-based embeddings can often match or even surpass the performance of a specialized EHR foundation model.<n>One of the tested LLM-based models achieves superior performance for disease onset, hospitalization, and mortality prediction.
  arXiv  Detail & Related papers  (2025-02-24T18:30:36Z)
• Health AI Developer Foundations [18.690656891269686]
  Health AI Developer Foundations (HAI-DEF) is a suite of pre-trained, domain-specific foundation models, tools, and recipes to accelerate building Machine Learning for health applications. Models cover various modalities and domains, including radiology (X-rays and computed tomography), histopathology, dermatological imaging, and audio. These models provide domain specific embeddings that facilitate AI development with less labeled data, shorter training times, and reduced computational costs.
  arXiv  Detail & Related papers  (2024-11-22T18:51:51Z)
• Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF [82.7679132059169]
  Reinforcement learning from human feedback has emerged as a central tool for language model alignment. We propose a new algorithm for online exploration in RLHF, Exploratory Preference Optimization (XPO) XPO enjoys the strongest known provable guarantees and promising empirical performance.
  arXiv  Detail & Related papers  (2024-05-31T17:39:06Z)
• Rethinking model prototyping through the MedMNIST+ dataset collection [0.11999555634662634]
  This work introduces a comprehensive benchmark for the MedMNIST+ dataset collection.<n>We reassess commonly used Convolutional Neural Networks (CNNs) and Vision Transformer (ViT) architectures across distinct medical datasets.<n>Our findings suggest that computationally efficient training schemes and modern foundation models offer viable alternatives to costly end-to-end training.
  arXiv  Detail & Related papers  (2024-04-24T10:19:25Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Secrets of RLHF in Large Language Models Part I: PPO [81.01936993929127]
  Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. reinforcement learning with human feedback (RLHF) emerges as the pivotal technological paradigm underpinning this pursuit. In this report, we dissect the framework of RLHF, re-evaluate the inner workings of PPO, and explore how the parts comprising PPO algorithms impact policy agent training.
  arXiv  Detail & Related papers  (2023-07-11T01:55:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.