Unified Reinforcement and Imitation Learning for Vision-Language Models

• URL: http://arxiv.org/abs/2510.19307v1
• Date: Wed, 22 Oct 2025 07:12:14 GMT
• Title: Unified Reinforcement and Imitation Learning for Vision-Language Models
• Authors: Byung-Kwan Lee, Ryo Hachiuma, Yong Man Ro, Yu-Chiang Frank Wang, Yueh-Hua Wu,
• Abstract summary: Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments.<n>This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel and efficient training algorithm designed to create powerful, lightweight VLMs.
• Score: 84.84277196012907
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel and efficient training algorithm designed to create powerful, lightweight VLMs. RIL distinctively combines the strengths of reinforcement learning with adversarial imitation learning. This enables smaller student VLMs not only to mimic the sophisticated text generation of large teacher models but also to systematically improve their generative capabilities through reinforcement signals. Key to our imitation framework is an LLM-based discriminator that adeptly distinguishes between student and teacher outputs, complemented by guidance from multiple large teacher VLMs to ensure diverse learning. This unified learning strategy, leveraging both reinforcement and imitation, empowers student models to achieve significant performance gains, making them competitive with leading closed-source VLMs. Extensive experiments on diverse vision-language benchmarks demonstrate that RIL significantly narrows the performance gap with state-of-the-art open- and closed-source VLMs and, in several instances, surpasses them.

Related papers

• Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration [35.429026246760635]
  BeMyEyes is a modular framework for extending Large Language Models (LLMs) to multimodal reasoning.<n>By combining the complementary strengths of perception and reasoning agents, BeMyEyes avoids the need for training large-scale multimodal models.<n> Experiments show that our framework unlocks the multimodal reasoning capabilities for LLMs.
  arXiv  Detail & Related papers  (2025-11-24T18:55:16Z)
• Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards [33.911792632604424]
  This paper explores two distinct AI-driven reward strategies within a Reinforcement Learning from AI Feedback framework.<n>The first strategy employs a RM trained on high-quality preference data curated by a novel multi-agent rejection sampling framework.<n>The second strategy utilizes a principle-guided LLM-as-a-Judge, whose reward function is optimized via an adversarial training scheme.
  arXiv  Detail & Related papers  (2025-08-29T10:00:55Z)
• PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning [54.73049408950049]
  We propose a Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning.<n>Our approach improves unified multimodal retrieval from both structural and learning perspectives.
  arXiv  Detail & Related papers  (2025-07-10T16:47:25Z)
• A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models [103.88578274567784]
  Motivation-enhanced Reinforcement Finetuning (MeRF) is an intuitive yet effective method enhancing reinforcement finetuning of Large Reasoning Models.<n>MeRF directly injects the reward specification into the prompt, which serves as an in-context motivation for the model to be aware of the optimization objective.<n>MeRF achieves substantial performance gains over RLVR baseline.
  arXiv  Detail & Related papers  (2025-06-23T10:37:57Z)
• GenRecal: Generation after Recalibration from Large to Small Vision-Language Models [63.27511432647797]
  Vision-language models (VLMs) have leveraged large language models (LLMs) to achieve performance on par with closed-source systems like GPT-4V.<n>Recent advancements in vision-language models (VLMs) have leveraged large language models (LLMs) to achieve performance on par with closed-source systems like GPT-4V.
  arXiv  Detail & Related papers  (2025-06-18T17:59:49Z)
• Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning [12.728451197053321]
  We propose Curriculum Reinforcement Finetuning (Curr-ReFT), a novel post-training paradigm specifically designed for small-scale vision-language models (VLMs)<n>Curr-ReFT comprises two sequential stages: Curriculum Reinforcement Learning and Rejected Sampling-based Self-improvement.<n>Our experiments demonstrate that models trained with Curr-ReFT paradigm achieve state-of-the-art performance across various visual tasks.
  arXiv  Detail & Related papers  (2025-03-10T08:48:50Z)
• VladVA: Discriminative Fine-tuning of LVLMs [67.14293827774827]
  Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning.<n>We propose to combine "the best of both worlds": a new training approach for discriminative fine-tuning of LVLMs.
  arXiv  Detail & Related papers  (2024-12-05T17:54:27Z)
• LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation [72.02635550088546]
  This work explores how large language models (LLMs) can enhance CLIP's capability, especially for processing longer and more complex image captions.<n>We introduce a caption-to-caption contrastive fine-tuning framework, significantly enhancing the discriminative quality of LLM outputs.<n>Our approach outperforms LoRA-based methods, achieving nearly fourfold faster training with superior performance.
  arXiv  Detail & Related papers  (2024-11-07T18:59:16Z)
• LLaVA-KD: A Framework of Distilling Multimodal Large Language Models [72.68665884790002]
  We propose a novel framework to transfer knowledge from l-MLLMs to s-MLLMs.<n>We introduce Multimodal Distillation (MDist) to transfer teacher model's robust representations across both visual and linguistic modalities.<n>We also propose a three-stage training scheme to fully exploit the potential of the proposed distillation strategy.
  arXiv  Detail & Related papers  (2024-10-21T17:41:28Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)

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.