Diving into Self-Evolving Training for Multimodal Reasoning

• URL: http://arxiv.org/abs/2412.17451v3
• Date: Fri, 06 Jun 2025 10:36:59 GMT
• Title: Diving into Self-Evolving Training for Multimodal Reasoning
• Authors: Wei Liu, Junlong Li, Xiwen Zhang, Fan Zhou, Yu Cheng, Junxian He,
• Abstract summary: Self-evolving trainin has emerged as a key approach for complex reasoning tasks.<n>This paper reframes self-evolving training for multimodal reasoning through the lens of reinforcement learning.<n>We propose M-STAR, a framework that achieves consistent performance gains across models of varying sizes and diverse benchmarks.
• Score: 36.70979791148913
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-evolving trainin--where models iteratively learn from their own outputs--has emerged as a key approach for complex reasoning tasks, addressing the scarcity of high-quality chain-of-thought data. However, its effectiveness in multimodal reasoning, a domain more intricate than text-only reasoning, remains underexplored, and the understanding of critical factors in this training paradigm remains limited. Furthermore, a central challenge for this training method is performance saturation, which impedes further improvements and scalability. Inspired by reinforcement learning (RL), in this paper, we reframe self-evolving training for multimodal reasoning through the lens of RL, identifying three pivotal factors: Training Method, Reward Model, and Prompt Variation. Through systematic analysis, we establish relatively optimal design principles that significantly enhance multimodal reasoning capabilities. Moreover, delving deeper into training dynamics, we uncover the roots of saturation and propose a new automatic balancing mechanism to mitigate this limitation. Building on these insights, we propose M-STAR (Multimodal Self-evolving Training for Reasoning), a framework that achieves consistent performance gains across models of varying sizes and diverse benchmarks. All resources are made publicly available at https://mstar-lmm.github.io.

Related papers

• VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning [69.44871115752055]
  We propose an advanced multimodal reasoning model trained via a novel Progressive Curriculum Reinforcement Learning (PCuRL) framework.<n>PCuRL systematically guides the model through tasks of gradually increasing difficulty, substantially improving its reasoning abilities across diverse multimodal contexts.<n>The framework introduces two key innovations: (1) an online difficulty soft weighting mechanism, dynamically adjusting training difficulty across successive RL training stages; and (2) a dynamic length reward mechanism, which encourages the model to adaptively regulate its reasoning path length according to task complexity.
  arXiv  Detail & Related papers  (2025-07-30T12:23:21Z)
• Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning [28.92744927199283]
  ReVisual-R1 achieves a new state-of-the-art among open-source 7B MLLMs on challenging benchmarks including MathVerse, MathVision, WeMath, LogicVista, DynaMath, and challenging AIME2024 and AIME2025.
  arXiv  Detail & Related papers  (2025-06-04T17:51:08Z)
• Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start [24.244577648817188]
  "aha moment" patterns are often attributed to emergent properties from reinforcement learning (RL)<n>We present a comprehensive study on enhancing multimodal reasoning through a two-stage approach.<n>Our experiments show that this combined approach consistently outperforms both SFT-only and RL-only methods.
  arXiv  Detail & Related papers  (2025-05-28T13:21:38Z)
• Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning [58.86928947970342]
  Embodied-R is a framework combining large-scale Vision-Language Models for perception and small-scale Language Models for reasoning.<n>After training on only 5k embodied video samples, Embodied-R with a 3B LM matches state-of-the-art multimodal reasoning models.<n>Embodied-R also exhibits emergent thinking patterns such as systematic analysis and contextual integration.
  arXiv  Detail & Related papers  (2025-04-17T06:16:11Z)
• Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition [89.50068130832635]
  Self-Improving cognition (SIcog) is a self-learning framework for constructing next-generation foundation MLLMs by multimodal knowledge.<n>We propose Chain-of-Description for step-by-step visual understanding and integrate structured Chain-of-Thought (CoT) reasoning to support in-depth multimodal reasoning.<n>Experiments demonstrate SIcog's effectiveness in developing MLLMs with enhanced multimodal cognition.
  arXiv  Detail & Related papers  (2025-03-16T00:25:13Z)
• VisualPRM: An Effective Process Reward Model for Multimodal Reasoning [76.35753243272521]
  We introduce VisualPRM, which improves the reasoning abilities of existing Multimodal Large Language Models (MLLMs) Our model achieves a 5.9-point improvement across seven multimodal reasoning benchmarks. For the evaluation of multimodal PRMs, we propose VisualProcessBench, a benchmark with human-annotated step-wise correctness labels.
  arXiv  Detail & Related papers  (2025-03-13T12:03:37Z)
• DeepSuM: Deep Sufficient Modality Learning Framework [6.455939667961427]
  We propose a novel framework for modality selection that independently learns the representation of each modality. Our framework aims to enhance the efficiency and effectiveness of multimodal learning by optimizing modality integration and selection.
  arXiv  Detail & Related papers  (2025-03-03T16:48:59Z)
• Progressive Multimodal Reasoning via Active Retrieval [64.74746997923967]
  Multi-step multimodal reasoning tasks pose significant challenges for large language models (MLLMs)<n>We propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs.<n>We show that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.
  arXiv  Detail & Related papers  (2024-12-19T13:25:39Z)
• RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models [60.596005921295806]
  Agglomerative models have emerged as a powerful approach to training vision foundation models.<n>We identify critical challenges including resolution mode shifts, teacher imbalance, idiosyncratic teacher artifacts, and an excessive number of output tokens.<n>We propose several novel solutions: multi-resolution training, mosaic augmentation, and improved balancing of teacher loss functions.
  arXiv  Detail & Related papers  (2024-12-10T17:06:41Z)
• HEMM: Holistic Evaluation of Multimodal Foundation Models [91.60364024897653]
  Multimodal foundation models can holistically process text alongside images, video, audio, and other sensory modalities. It is challenging to characterize and study progress in multimodal foundation models, given the range of possible modeling decisions, tasks, and domains.
  arXiv  Detail & Related papers  (2024-07-03T18:00:48Z)
• Beyond Unimodal Learning: The Importance of Integrating Multiple Modalities for Lifelong Learning [23.035725779568587]
  We study the role and interactions of multiple modalities in mitigating forgetting in deep neural networks (DNNs) Our findings demonstrate that leveraging multiple views and complementary information from multiple modalities enables the model to learn more accurate and robust representations. We propose a method for integrating and aligning the information from different modalities by utilizing the relational structural similarities between the data points in each modality.
  arXiv  Detail & Related papers  (2024-05-04T22:02:58Z)
• Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training [49.3242278912771]
  Multimodal reasoning is a challenging task that requires models to reason across multiple modalities to answer questions. Existing approaches have made progress by incorporating language and visual modalities into a two-stage reasoning framework. We propose MC-CoT, a self-consistency training strategy that generates multiple rationales and answers, subsequently selecting the most accurate through a voting process.
  arXiv  Detail & Related papers  (2023-11-23T17:09:48Z)
• Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [62.70450216120704]
  Unsupervised pre-training has shown great success in skeleton-based action understanding. We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL. UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
  arXiv  Detail & Related papers  (2023-11-06T13:56:57Z)
• Improving Discriminative Multi-Modal Learning with Large-Scale Pre-Trained Models [51.5543321122664]
  This paper investigates how to better leverage large-scale pre-trained uni-modal models to enhance discriminative multi-modal learning. We introduce Multi-Modal Low-Rank Adaptation learning (MMLoRA)
  arXiv  Detail & Related papers  (2023-10-08T15:01:54Z)
• On Uni-Modal Feature Learning in Supervised Multi-Modal Learning [21.822251958013737]
  We abstract the features (i.e. learned representations) of multi-modal data into 1) uni-modal features, which can be learned from uni-modal training, and 2) paired features, which can only be learned from cross-modal interactions. We demonstrate that, under a simple guiding strategy, we can achieve comparable results to other complex late-fusion or intermediate-fusion methods on various multi-modal datasets.
  arXiv  Detail & Related papers  (2023-05-02T07:15:10Z)
• Multimodal Contrastive Learning via Uni-Modal Coding and Cross-Modal Prediction for Multimodal Sentiment Analysis [19.07020276666615]
  We propose a novel framework named MultiModal Contrastive Learning (MMCL) for multimodal representation to capture intra- and inter-modality dynamics simultaneously. We also design two contrastive learning tasks, instance- and sentiment-based contrastive learning, to promote the process of prediction and learn more interactive information related to sentiment.
  arXiv  Detail & Related papers  (2022-10-26T08:24:15Z)
• MultiViz: An Analysis Benchmark for Visualizing and Understanding Multimodal Models [103.9987158554515]
  MultiViz is a method for analyzing the behavior of multimodal models by scaffolding the problem of interpretability into 4 stages. We show that the complementary stages in MultiViz together enable users to simulate model predictions, assign interpretable concepts to features, perform error analysis on model misclassifications, and use insights from error analysis to debug models.
  arXiv  Detail & Related papers  (2022-06-30T18:42:06Z)

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.