MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

• URL: http://arxiv.org/abs/2603.09206v1
• Date: Tue, 10 Mar 2026 05:23:26 GMT
• Title: MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
• Abstract summary: We present Multi-model Multimodal Zero (MM-Zero), the first RL-based framework to achieve zero-data self-evolution for Vision Language Models.<n> MM-Zero introduces a multi-role self-evolving training framework comprising three specialized roles.<n>Our experiments show that MM-Zero improves VLM reasoning performance across a wide range of multimodal benchmarks.
• Score: 30.295273919299046
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Self-evolving has emerged as a key paradigm for improving foundational models such as Large Language Models (LLMs) and Vision Language Models (VLMs) with minimal human intervention. While recent approaches have demonstrated that LLM agents can self-evolve from scratch with little to no data, VLMs introduce an additional visual modality that typically requires at least some seed data, such as images, to bootstrap the self-evolution process. In this work, we present Multi-model Multimodal Zero (MM-Zero), the first RL-based framework to achieve zero-data self-evolution for VLM reasoning. Moving beyond prior dual-role (Proposer and Solver) setups, MM-Zero introduces a multi-role self-evolving training framework comprising three specialized roles: a Proposer that generates abstract visual concepts and formulates questions; a Coder that translates these concepts into executable code (e.g., Python, SVG) to render visual images; and a Solver that performs multimodal reasoning over the generated visual content. All three roles are initialized from the same base model and trained using Group Relative Policy Optimization (GRPO), with carefully designed reward mechanisms that integrate execution feedback, visual verification, and difficulty balancing. Our experiments show that MM-Zero improves VLM reasoning performance across a wide range of multimodal benchmarks. MM-Zero establishes a scalable path toward self-evolving multi-model systems for multimodal models, extending the frontier of self-improvement beyond the conventional two-model paradigm.

Related papers

• Analyzing Diffusion and Autoregressive Vision Language Models in Multimodal Embedding Space [52.34072027212278]
  Embedding models are a fundamental component of modern AI systems such as semantic search and retrieval-augmented generation.<n>Recent advances in large foundation models have substantially accelerated the development of embedding models.<n>We present the first systematic study of converting Multimodal dLLMs into embedding models.
  arXiv  Detail & Related papers  (2026-01-19T06:51:15Z)
• EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards [52.42920996842378]
  We propose a self-evolving framework, named EvoLMM, that instantiates two cooperative agents from a single backbone model.<n>This dynamic feedback encourages both the generation of informative queries and the refinement of structured reasoning.<n>Our code and models are available at https://github.com/mbzuai-oryx/EvoLMM.
  arXiv  Detail & Related papers  (2025-11-20T18:59:54Z)
• VisPlay: Self-Evolving Vision-Language Models from Images [16.43670977857598]
  Reinforcement learning (RL) provides a principled framework for improving Vision-Language Models (VLMs) on complex tasks.<n>We introduce VisPlay, a self-evolving RL framework that enablesVLMs to autonomously improve their reasoning abilities using large amounts of unlabeled image data.
  arXiv  Detail & Related papers  (2025-11-19T17:55:15Z)
• OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging [124.91183814854126]
  Model merging seeks to combine multiple expert models into a single model.<n>We introduce a benchmark for model merging research that clearly divides the tasks for MLLM training and evaluation.<n>We find that model merging offers a promising way for building improved MLLMs without requiring training data.
  arXiv  Detail & Related papers  (2025-05-26T12:23:14Z)
• Enhanced Continual Learning of Vision-Language Models with Model Fusion [16.764069327701186]
  Vision-Language Models (VLMs) represent a breakthrough in artificial intelligence.<n>VLMs are susceptible to catastrophic forgetting when sequentially fine-tuned on multiple downstream tasks.<n>We propose Continual Decoupling-Unifying (ConDU), a novel approach, by introducing model fusion into continual learning.
  arXiv  Detail & Related papers  (2025-03-12T15:48:13Z)
• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [61.143381152739046]
  We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach.<n>Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations.<n>We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
  arXiv  Detail & Related papers  (2024-06-24T17:59:42Z)
• Multi-modal Auto-regressive Modeling via Visual Words [96.25078866446053]
  We propose the concept of visual tokens, which maps the visual features to probability distributions over Large Multi-modal Models' vocabulary. We further explore the distribution of visual features in the semantic space within LMM and the possibility of using text embeddings to represent visual information.
  arXiv  Detail & Related papers  (2024-03-12T14:58:52Z)
• eP-ALM: Efficient Perceptual Augmentation of Language Models [70.47962271121389]
  We propose to direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. We show that by freezing more than 99% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning.
  arXiv  Detail & Related papers  (2023-03-20T19:20:34Z)

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.