Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning

• URL: http://arxiv.org/abs/2603.27482v1
• Date: Sun, 29 Mar 2026 02:31:12 GMT
• Title: Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning
• Abstract summary: We propose Differential Feedback, which automatically constructs token/step-level supervision masks by repairing erroneous reasoning trajectories.<n>Our approach offers an effective, low-cost solution for accurate vision--reasoning process alignment.
• Score: 10.473880989969844
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style training. However, relying solely on terminal outcome rewards yields sparse credit assignment in multi-step reasoning, weakening the linkage between visual evidence and intermediate steps and often causing unstable optimization and visual hallucinations. We propose Differential Feedback, which automatically constructs token/step-level supervision masks by repairing erroneous reasoning trajectories, explicitly marking the key positions that require correction. Without costly large-scale step-by-step human annotations, our method enables process-level visual alignment and can be seamlessly integrated into existing GRPO-like frameworks. Experiments on multimodal reasoning benchmarks including MMMStar and MathVista show an average 3% improvement under matched compute budgets. Our approach offers an effective, low-cost solution for accurate vision--reasoning process alignment.

Related papers

• GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models [19.21570577065149]
  In Vision-Language Models (VLMs) processing a massive number of visual tokens incurs prohibitive computational retraining.<n>GRIP-VLM employs a Group Relative Policy (GRPO) paradigm anchored by supervised pruning to directly explore space selection.
  arXiv  Detail & Related papers  (2026-05-13T11:32:03Z)
• Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training [82.17582358979884]
  Post-training with explicit reasoning traces is common to improve the reasoning capabilities of Multimodal Large Language Models (MLLMs)<n>We propose VISTA, a vision-aware self-improvement training framework for enhancing the multimodal reasoning of MLLMs.
  arXiv  Detail & Related papers  (2026-05-12T10:44:35Z)
• Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models [54.597200388738656]
  Reward-based fine-tuning aims to steer a pretrained diffusion or flow-based generative model toward higher-reward samples.<n>We show that many can be written under a common framework, which we call reward score matching (RSM)
  arXiv  Detail & Related papers  (2026-04-19T12:47:52Z)
• VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models [74.05545957865228]
  Visual token pruning methods effectively mitigate the quadratic computational growth caused by processing high-resolution images and video frames in vision-language models (VLMs)<n>We introduce, a novel framework that formulates visual token pruning as a Pareto configuration optimization problem to automatically identify optimal configurations.<n>Our approach employs continuous relaxation and straight-through estimators to enable gradient-based search, solved via the Augmented Lagrangian method.
  arXiv  Detail & Related papers  (2026-04-16T16:21:05Z)
• Perception-Aware Multimodal Spatial Reasoning from Monocular Images [57.42071289037214]
  spatial reasoning from monocular images is essential for autonomous driving.<n>Current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception.<n>We propose a perception-aware multimodal reasoning framework that equipsVLMs with explicit object-centric grounding ability.
  arXiv  Detail & Related papers  (2026-03-07T02:05:12Z)
• PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment [29.229662966154507]
  PaLMR is a framework that aligns not only outcomes but also the reasoning process itself.<n> Experiments on Qwen2.5-VL-7B show that our approach substantially reduces reasoning hallucinations and improves visual reasoning fidelity.<n>These findings indicate that PaLMR offers a principled and practical route to process-aligned multimodal reasoning.
  arXiv  Detail & Related papers  (2026-02-28T04:33:11Z)
• PROPA: Toward Process-level Optimization in Visual Reasoning via Reinforcement Learning [30.44007644340425]
  We introduce PROPA, a novel framework that integrates Monte Carlo Tree Search (MCTS) with GRPO to generate dense, process-level rewards and optimize reasoning at each intermediate step without human annotations.<n>Across seven benchmarks and four VLM backbones, PROPA consistently outperforms both SFT- and RLVR-based baselines.<n>It achieves up to 17.0% gains on in-domain tasks and 21.0% gains on out-of-domain tasks compared to existing state-of-the-art.
  arXiv  Detail & Related papers  (2025-11-13T13:06:12Z)
• Perception-Aware Policy Optimization for Multimodal Reasoning [79.56070395437898]
  A major source of error in current multimodal reasoning lies in the perception of visual inputs.<n>We propose PAPO, a novel policy gradient algorithm that encourages the model to learn to perceive while learning to reason.<n>We observe a substantial reduction of 30.5% in perception errors, indicating improved perceptual capabilities with PAPO.
  arXiv  Detail & Related papers  (2025-07-08T23:22:34Z)
• ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding [71.654781631463]
  ReAgent-V is a novel agentic video understanding framework.<n>It integrates efficient frame selection with real-time reward generation during inference.<n>Extensive experiments on 12 datasets demonstrate significant gains in generalization and reasoning.
  arXiv  Detail & Related papers  (2025-06-02T04:23:21Z)
• Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization [40.77611907215627]
  Large Vision Language Models (VLMs) are prone to significant hallucinations, particularly in the form of cross-modal inconsistencies.<n>We introduce Re-Align, a novel alignment framework that leverages image retrieval to construct a dual-preference dataset.<n>We also introduce rDPO, an extension of the standard direct preference optimization that incorporates an additional visual preference objective during fine-tuning.
  arXiv  Detail & Related papers  (2025-02-18T18:59:57Z)
• Transparent and Coherent Procedural Mistake Detection [30.540514590818265]
  Procedural mistake detection (PMD) is a challenging problem of classifying whether a human user has successfully executed a task (specified by a procedural text)<n>We extend PMD to require generating visual self-dialog rationales to inform decisions.<n>Given the impressive, mature image understanding capabilities observed in recent vision-and-language models (VLMs), we curate a suitable benchmark dataset for PMD based on individual frames.
  arXiv  Detail & Related papers  (2024-12-16T16:13:55Z)
• In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement [71.60563181678323]
  Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality.<n>To handle these challenges, a direct solution is to generate high-confidence'' data from unsupervised downstream tasks.<n>We propose a novel approach, pseudo-supervised demonstrations aligned prompt optimization (PAPO) algorithm, which jointly refines both the prompt and the overall pseudo-supervision.
  arXiv  Detail & Related papers  (2024-10-04T03:39:28Z)
• Debiasing Multimodal Large Language Models via Penalization of Language Priors [38.97645845493758]
  Multimodal Large Language Models (MLLMs) have become indispensable tools in computer vision and natural language processing.<n>Despite their advancements, our investigation reveals a noteworthy bias: the generated content is often driven more by the inherent priors of the underlying Large Language Models (LLMs) than by the input image.<n>We propose two simple, training-free strategies to rectify these biases and redirect the model's focus toward visual information.
  arXiv  Detail & Related papers  (2024-03-08T12:35:07Z)

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.