Co-Reinforcement Learning for Unified Multimodal Understanding and Generation

• URL: http://arxiv.org/abs/2505.17534v2
• Date: Sat, 31 May 2025 13:51:12 GMT
• Title: Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
• Authors: Jingjing Jiang, Chongjie Si, Jun Luo, Hanwang Zhang, Chao Ma,
• Abstract summary: This paper presents a pioneering exploration of reinforcement learning (RL) via group relative policy optimization for unified multimodal large language models (ULMs)<n>We introduce CoRL, a co-reinforcement learning framework comprising a unified RL stage for joint optimization and a refined RL stage for task-specific enhancement.<n>With the proposed CoRL, our resulting model, ULM-R1, achieves average improvements of 7% on three text-to-image generation datasets and 23% on nine multimodal understanding benchmarks.
• Score: 53.03303124157899
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents a pioneering exploration of reinforcement learning (RL) via group relative policy optimization for unified multimodal large language models (ULMs), aimed at simultaneously reinforcing generation and understanding capabilities. Through systematic pilot studies, we uncover the significant potential of ULMs to enable the synergistic co-evolution of dual capabilities within a shared policy optimization framework. Building on this insight, we introduce CoRL, a co-reinforcement learning framework comprising a unified RL stage for joint optimization and a refined RL stage for task-specific enhancement. With the proposed CoRL, our resulting model, ULM-R1, achieves average improvements of 7% on three text-to-image generation datasets and 23% on nine multimodal understanding benchmarks. These results demonstrate the effectiveness of CoRL and highlight the substantial benefit of reinforcement learning in facilitating cross-task synergy and optimization for ULMs. Code is available at https://github.com/mm-vl/ULM-R1.

Related papers

• RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization [86.30192066451256]
  We propose RL-PLUS, a novel hybrid-policy optimization approach for Large Language Models (LLMs)<n> RL-PLUS synergizes internal exploitation with external data to achieve stronger reasoning capabilities and surpass the boundaries of base models.<n>We provide both theoretical analysis and extensive experiments to demonstrate the superiority and generalizability of our approach.
  arXiv  Detail & Related papers  (2025-07-31T23:55:29Z)
• Omni-Thinker: Scaling Cross-Domain Generalization in LLMs via Multi-Task RL with Hybrid Rewards [50.21528417884747]
  We introduce Omni-Thinker, a unified reinforcement learning framework that enhances large language models (LLMs) performance across diverse tasks.<n>Our approach enables consistent optimization across task types and scales RL-based training to subjective domains.<n> Experimental results across four domains reveal that curriculum learning improves performance by 5.2% over joint training and 9.1% over model merging.
  arXiv  Detail & Related papers  (2025-07-20T01:50:16Z)
• Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs [51.21041884010009]
  Ring-lite is a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL)<n>Our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks.
  arXiv  Detail & Related papers  (2025-06-17T17:12:34Z)
• RLAE: Reinforcement Learning-Assisted Ensemble for LLMs [21.77261258691006]
  Large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks.<n>We propose Reinforcement Learning-Assisted Ensemble for LLMs, a novel framework that reformulates ensemble through the lens of a Markov Decision Process (MDP)<n>Our approach introduces a RL agent that dynamically adjusts ensemble weights by considering both input context and intermediate generation states.
  arXiv  Detail & Related papers  (2025-05-31T07:38:41Z)
• SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks [110.20297293596005]
  Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks.<n>Existing multi-turn RL algorithms for optimizing LLM agents fail to perform effective credit assignment over multiple turns while leveraging the generalization capabilities of LLMs.<n>We propose a novel RL algorithm, SWEET-RL, that uses a carefully designed optimization objective to train a critic model with access to additional training-time information.<n>Our experiments demonstrate that SWEET-RL achieves a 6% absolute improvement in success and win rates on ColBench compared to other state-of-the-art multi-turn RL algorithms.
  arXiv  Detail & Related papers  (2025-03-19T17:55:08Z)
• AmCLR: Unified Augmented Learning for Cross-Modal Representations [0.0]
  We introduce AmCLR and xAmCLR objective functions tailored for bimodal vision-language models.<n>These advancements yield a more resilient and generalizable contrastive learning process.
  arXiv  Detail & Related papers  (2024-12-10T23:32:36Z)
• Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning [13.753960633998389]
  Reinforcement learning (RL) has emerged as a pivotal technique for fine-tuning large language models (LLMs) on specific tasks.<n>In this paper, we propose CORY, extending the RL fine-tuning of LLMs to a sequential cooperative multi-agent reinforcement learning framework.<n>Results show that CORY outperforms PPO in terms of policy optimality, resistance to distribution collapse, and training robustness.
  arXiv  Detail & Related papers  (2024-10-08T14:55:26Z)
• Enhancing Spectrum Efficiency in 6G Satellite Networks: A GAIL-Powered Policy Learning via Asynchronous Federated Inverse Reinforcement Learning [67.95280175998792]
  A novel adversarial imitation learning (GAIL)-powered policy learning approach is proposed for optimizing beamforming, spectrum allocation, and remote user equipment (RUE) association ins. We employ inverse RL (IRL) to automatically learn reward functions without manual tuning. We show that the proposed MA-AL method outperforms traditional RL approaches, achieving a $14.6%$ improvement in convergence and reward value.
  arXiv  Detail & Related papers  (2024-09-27T13:05:02Z)
• Multi-turn Reinforcement Learning from Preference Human Feedback [41.327438095745315]
  Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models with human preferences.<n>Existing methods work by emulating the preferences at the single decision (turn) level.<n>We develop novel methods for Reinforcement Learning from preference feedback between two full multi-turn conversations.
  arXiv  Detail & Related papers  (2024-05-23T14:53:54Z)
• Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning [48.79569442193824]
  We show that COMRL algorithms are essentially optimizing the same mutual information objective between the task variable $M$ and its latent representation $Z$ by implementing various approximate bounds.<n>As demonstrations, we propose a supervised and a self-supervised implementation of $I(Z; M)$, and empirically show that the corresponding optimization algorithms exhibit remarkable generalization across a broad spectrum of RL benchmarks.<n>This work lays the information theoretic foundation for COMRL methods, leading to a better understanding of task representation learning in the context of reinforcement learning.
  arXiv  Detail & Related papers  (2024-02-04T09:58:42Z)
• M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic Manipulation [0.7564784873669823]
  We propose Multimodal Contrastive Unsupervised Reinforcement Learning (M2CURL) Our approach employs a novel multimodal self-supervised learning technique that learns efficient representations and contributes to faster convergence of RL algorithms. We evaluate M2CURL on the Tactile Gym 2 simulator and we show that it significantly enhances the learning efficiency in different manipulation tasks.
  arXiv  Detail & Related papers  (2024-01-30T14:09:35Z)
• PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policies [68.8204255655161]
  We propose a reinforcement learning based framework PoBRL for solving multi-document summarization. Our strategy decouples this multi-objective optimization into different subproblems that can be solved individually by reinforcement learning. Our empirical analysis shows state-of-the-art performance on several multi-document datasets.
  arXiv  Detail & Related papers  (2021-05-18T02:55:42Z)

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.