Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization
Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO) have significantly advanced the reasoning capabilities of large language models. Extending these methods to multimodal settings, however, faces a critical challenge: the instability of std-based normalization, which is easily distorted by extreme samples with nearly positive or negative rewards. Unlike pure-text LLMs, multimodal models are particularly sensitive to such distortions, as both perceptual and reasoning errors influence their responses. To address this, we characterize each sample by its difficulty, defined through perceptual complexity (measured via visual entropy) and reasoning uncertainty (captured by model confidence). Building on this characterization, we propose difficulty-aware group normalization (Durian), which re-groups samples by difficulty levels and shares the std within each group. Our approach preserves GRPO's intra-group distinctions while eliminating sensitivity to extreme cases, yielding significant performance gains across multiple multimodal reasoning benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningMultimodal ReasoningSimilar Papers 제목 키워드 기반
DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantage
Reinforcement learning (RL) with group relative policy optimization (GRPO) has become a widely adopted approach for enhancing the reasoning capabilities of multimodal large language models (MLLMs). While GRPO enables lon…
Reinforcement LearningMultimodal ReasoningObserve-R1: Unlocking Reasoning Abilities of MLLMs with Dynamic Progressive Reinforcement Learning
Reinforcement Learning (RL) has shown promise in improving the reasoning abilities of Large Language Models (LLMs). However, the specific challenges of adapting RL to multimodal data and formats remain relatively unexplo…
Reinforcement Learning (RL)APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization
Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data, but they often struggle with complex reasoning. While Reinforcement learning (RL) can boost reasoning in LLMs, applying it to MLLMs is tr…
Multimodal ReasoningReinforcement Learning (RL)Tailored Teaching with Balanced Difficulty: Elevating Reasoning in Multimodal Chain-of-Thought via Prompt Curriculum
The effectiveness of Multimodal Chain-of-Thought (MCoT) prompting is often limited by the use of randomly or manually selected examples. These examples fail to account for both model-specific knowledge distributions and …
Multimodal ReasoningActive LearningRevealing Multimodal Causality with Large Language Models
Uncovering cause-and-effect mechanisms from data is fundamental to scientific progress. While large language models (LLMs) show promise for enhancing causal discovery (CD) from unstructured data, their application to the…