Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning

• URL: http://arxiv.org/abs/2512.06835v1
• Date: Sun, 07 Dec 2025 13:17:31 GMT
• Title: Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning
• Authors: Tingyu Li, Zheng Sun, Jingxuan Wei, Siyuan Li, Conghui He, Lijun Wu, Cheng Tan,
• Abstract summary: Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL)<n>RL provides a feasible solution for realizing continuous self-evolving large vision-language models (LVLMs) in the era of experience.<n>Existing strategies such as synthetic data and self-rewarding mechanisms suffer from limited distributions and alignment difficulties.<n>We propose DoGe, a dual-decoupling framework that guides models to first learn from context rather than problem solving.
• Score: 41.523848964102
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL), which provides a feasible solution for realizing continuous self-evolving large vision-language models (LVLMs) in the era of experience. However, RL for VLMs requires abundant high-quality multimodal data, especially challenging in specialized domains like chemistry, earth sciences, and multimodal mathematics. Existing strategies such as synthetic data and self-rewarding mechanisms suffer from limited distributions and alignment difficulties, ultimately causing reward hacking: models exploit high-reward patterns, collapsing policy entropy and destabilizing training. We propose DoGe (Decouple to Generalize), a dual-decoupling framework that guides models to first learn from context rather than problem solving by refocusing on the problem context scenarios overlooked by synthetic data methods. By decoupling learning process into dual components (Thinker and Solver), we reasonably quantify the reward signals of this process and propose a two-stage RL post-training approach from freely exploring context to practically solving tasks. Second, to increase the diversity of training data, DoGe constructs an evolving curriculum learning pipeline: an expanded native domain knowledge corpus and an iteratively evolving seed problems pool. Experiments show that our method consistently outperforms the baseline across various benchmarks, providing a scalable pathway for realizing self-evolving LVLMs.

Related papers

• Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting [70.83781268763215]
  Vision-language models (VLMs) have achieved impressive performance across diverse multimodal tasks by leveraging large-scale pre-training.<n>VLMs face unique challenges such as cross-modal feature drift, parameter interference due to shared architectures, and zero-shot capability erosion.<n>This survey aims to serve as a comprehensive and diagnostic reference for researchers developing lifelong vision-language systems.
  arXiv  Detail & Related papers  (2025-08-06T09:03:10Z)
• 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)
• C2-Evo: Co-Evolving Multimodal Data and Model for Self-Improving Reasoning [78.36259648527401]
  C2-Evo is an automatic, closed-loop self-improving framework that jointly evolves both training data and model capabilities.<n>We show that C2-Evo consistently obtains considerable performance gains across multiple mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-07-22T12:27:08Z)
• Auto-Formulating Dynamic Programming Problems with Large Language Models [4.693833469789685]
  We introduce DP-Bench, the first benchmark covering a wide range of textbook-level DP problems to enable systematic evaluation.<n>Central to DPLM's effectiveness is DualReflect, our novel synthetic data generation pipeline, designed to scale up training data from a limited set of initial examples.<n>Our results reveal a key insight: backward generation is favored in low-data regimes for its strong correctness guarantees, while forward generation becomes increasingly valuable at scale for introducing diverse formulations.
  arXiv  Detail & Related papers  (2025-07-15T21:09:43Z)
• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning [17.459985667824807]
  Building on the success of text-based reasoning models like DeepSeek-R1, extending these capabilities to multimodal reasoning holds great promise.<n>In this paper, we show how to achieve the general-purpose visual-language reasoning through reinforcement learning.
  arXiv  Detail & Related papers  (2025-06-09T16:20:54Z)
• mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation [15.991125806837386]
  Large Vision-Language Models (LVLMs) have made remarkable strides in multimodal tasks such as visual question answering, visual grounding, and complex reasoning.<n>Retrieval-Augmented Generation (RAG) offers a practical solution to mitigate these challenges by allowing the LVLMs to access large-scale knowledge databases via retrieval mechanisms.
  arXiv  Detail & Related papers  (2025-05-29T23:32:03Z)
• Continual Multimodal Contrastive Learning [99.53621521696051]
  Multimodal Contrastive Learning (MCL) advances in aligning different modalities and generating multimodal representations in a joint space.<n>However, a critical yet often overlooked challenge remains: multimodal data is rarely collected in a single process, and training from scratch is computationally expensive.<n>In this paper, we formulate CMCL through two specialized principles of stability and plasticity.<n>We theoretically derive a novel optimization-based method, which projects updated gradients from dual sides onto subspaces where any gradient is prevented from interfering with the previously learned knowledge.
  arXiv  Detail & Related papers  (2025-03-19T07:57:08Z)
• Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning [79.46570165281084]
  We propose a Multi-Stage Knowledge Integration network (MulKI) to emulate the human learning process in distillation methods. MulKI achieves this through four stages, including Eliciting Ideas, Adding New Ideas, Distinguishing Ideas, and Making Connections. Our method demonstrates significant improvements in maintaining zero-shot capabilities while supporting continual learning across diverse downstream tasks.
  arXiv  Detail & Related papers  (2024-11-11T07:36:19Z)
• Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework [58.362064122489166]
  This paper introduces the Cross-modal Few-Shot Learning task, which aims to recognize instances across multiple modalities while relying on scarce labeled data.<n>We propose a Generative Transfer Learning framework by simulating how humans abstract and generalize concepts.<n>We show that the GTL achieves state-of-the-art performance across seven multi-modal datasets across RGB-Sketch, RGB-Infrared, and RGB-Depth.
  arXiv  Detail & Related papers  (2024-10-14T16:09:38Z)

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.