VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought

• URL: http://arxiv.org/abs/2505.16192v2
• Date: Fri, 30 May 2025 06:35:34 GMT
• Title: VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought
• Authors: Chaoya Jiang, Yongrui Heng, Wei Ye, Han Yang, Haiyang Xu, Ming Yan, Ji Zhang, Fei Huang, Shikun Zhang,
• Abstract summary: We introduce textbfVLM-R$3$ (textbfVisual textbfLanguage textbfModel with textbfRegion textbfRecognition and textbfReasoning), a framework that equips an MLLM with the ability to decide emph when additional visual evidence is needed.<n>Experiments on MathVista, ScienceQA, and other benchmarks show that VLM-R$3$ sets a new
• Score: 51.43082554363725
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, reasoning-based MLLMs have achieved a degree of success in generating long-form textual reasoning chains. However, they still struggle with complex tasks that necessitate dynamic and iterative focusing on and revisiting of visual regions to achieve precise grounding of textual reasoning in visual evidence. We introduce \textbf{VLM-R$^3$} (\textbf{V}isual \textbf{L}anguage \textbf{M}odel with \textbf{R}egion \textbf{R}ecognition and \textbf{R}easoning), a framework that equips an MLLM with the ability to (i) decide \emph{when} additional visual evidence is needed, (ii) determine \emph{where} to ground within the image, and (iii) seamlessly weave the relevant sub-image content back into an interleaved chain-of-thought. The core of our method is \textbf{Region-Conditioned Reinforcement Policy Optimization (R-GRPO)}, a training paradigm that rewards the model for selecting informative regions, formulating appropriate transformations (e.g.\ crop, zoom), and integrating the resulting visual context into subsequent reasoning steps. To bootstrap this policy, we compile a modest but carefully curated Visuo-Lingual Interleaved Rationale (VLIR) corpus that provides step-level supervision on region selection and textual justification. Extensive experiments on MathVista, ScienceQA, and other benchmarks show that VLM-R$^3$ sets a new state of the art in zero-shot and few-shot settings, with the largest gains appearing on questions demanding subtle spatial reasoning or fine-grained visual cue extraction.

Related papers

• MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization [19.70803794316208]
  Medical Image Grounding (MIG) involves localizing specific regions in medical images based on textual descriptions.<n>Existing Vision-Language Models (VLMs) for MIG often rely on Supervised Fine-Tuning (SFT) with large amounts of Chain-of-Thought (CoT) reasoning annotations.<n>We propose the Spatial-Semantic Rewarded Group Relative Policy Optimization to train the model without CoT reasoning annotations.
  arXiv  Detail & Related papers  (2025-07-01T21:51:42Z)
• VGR: Visual Grounded Reasoning [24.19194463566865]
  This paper introduces VGR, a novel reasoning multimodal large language model (MLLM) with enhanced fine-grained visual perception capabilities.<n>Unlike traditional MLLMs that answer the question or reasoning solely on the language space, our VGR first detects relevant regions that may help to solve problems, and then provides precise answers based on replayed image regions.
  arXiv  Detail & Related papers  (2025-06-13T17:47:43Z)
• Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing [62.447497430479174]
  Drawing to reason in space is a novel paradigm that enables LVLMs to reason through elementary drawing operations in the visual space.<n>Our model, named VILASR, consistently outperforms existing methods across diverse spatial reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T17:41:50Z)
• Perceptual Decoupling for Scalable Multi-modal Reasoning via Reward-Optimized Captioning [78.17782197231325]
  We propose a reasoning-guided reinforcement learning strategy that aligns the extractor's captioning behavior with the reasoning objective.<n> Experiments on multi-modal math and science benchmarks show that the proposed RACRO method achieves state-of-the-art average performance.
  arXiv  Detail & Related papers  (2025-06-05T02:28:07Z)
• SVQA-R1: Reinforcing Spatial Reasoning in MLLMs via View-Consistent Reward Optimization [57.484274282231226]
  We propose SVQA-R1, the first framework to extend R1-style training to spatial VQA.<n>In particular, we introduce Spatial-GRPO, a novel group-wise RL strategy that constructs view-consistent rewards by perturbing spatial relations between objects.<n>Our model, SVQA-R1, not only dramatically improved accuracy on spatial VQA benchmarks but also exhibits interpretable reasoning paths even without using supervised fine-tuning data.
  arXiv  Detail & Related papers  (2025-06-02T06:58:43Z)
• From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection [38.98491521357191]
  textbfABS achieves state-of-the-art performance on out-of-distribution generalization and zero-shot classification tasks.<n>textbfABS is training-free and even rivals few-shot and test-time adaptation methods.
  arXiv  Detail & Related papers  (2025-05-19T15:15:37Z)
• EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks [24.41705039390567]
  EmbodiedVSR (Embodied Visual Spatial Reasoning) is a novel framework that integrates dynamic scene graph-guided Chain-of-Thought (CoT) reasoning.<n>Our method enables zero-shot spatial reasoning without task-specific fine-tuning.<n>Experiments demonstrate that our framework significantly outperforms existing MLLM-based methods in accuracy and reasoning coherence.
  arXiv  Detail & Related papers  (2025-03-14T05:06:07Z)
• Relation-aware Hierarchical Prompt for Open-vocabulary Scene Graph Generation [14.82606425343802]
  Open-vocabulary Scene Graph Generation (OV-SGG) overcomes the limitations of the closed-set assumption by aligning visual relationship representations with open-vocabulary textual representations.<n>Existing OV-SGG methods are constrained by fixed text representations, limiting diversity and accuracy in image-text alignment.<n>We propose the Relation-Aware Hierarchical Prompting (RAHP) framework, which enhances text representation by integrating subject-object and region-specific relation information.
  arXiv  Detail & Related papers  (2024-12-26T02:12:37Z)
• ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models [73.34709921061928]
  We propose a training-free method to inject visual prompts into Multimodal Large Language Models (MLLMs)<n>We optimize a learnable latent variable based on an energy function, enhancing the strength of referring regions in the attention map.<n>Our method offers a promising direction for integrating referring abilities into MLLMs, and supports referring with box, mask, scribble and point.
  arXiv  Detail & Related papers  (2024-07-31T11:40:29Z)
• Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
  multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs. This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
  arXiv  Detail & Related papers  (2024-07-05T17:43:30Z)
• DRTR: Distance-Aware Graph Representation Learning [6.185573921868495]
  We propose textbfDRTR, a novel graph learning framework that integrates distance-aware multi-hop message passing with dynamic topology refinement.<n>A emphDistance Recomputator prunes semantically weak edges using adaptive attention, while a emphTopology Reconstructor establishes latent connections among distant but relevant nodes.
  arXiv  Detail & Related papers  (2024-06-25T05:12:51Z)
• Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training [79.27663870280038]
  We introduce Contrastive Region Guidance (CRG), a training-free guidance method that enables open-source vision-language models to respond to visual prompts. When region annotations are provided, CRG increases absolute accuracy by up to 11.1% on ViP-Bench. We also show CRG's applicability to spatial reasoning, with 10% improvement on What'sUp.
  arXiv  Detail & Related papers  (2024-03-04T18:55:30Z)
• Improving Vision-and-Language Reasoning via Spatial Relations Modeling [30.477235227733928]
  Visual commonsense reasoning (VCR) is a challenging multi-modal task. The proposed method can guide the representations to maintain more spatial context. We achieve the state-of-the-art results on VCR and two other vision-and-language reasoning tasks VQA, and NLVR.
  arXiv  Detail & Related papers  (2023-11-09T11:54:55Z)
• Vision-by-Language for Training-Free Compositional Image Retrieval [78.60509831598745]
  Compositional Image Retrieval (CIR) aims to retrieve the relevant target image in a database. Recent research sidesteps this need by using large-scale vision-language models (VLMs) We propose to tackle CIR in a training-free manner via Vision-by-Language (CIReVL)
  arXiv  Detail & Related papers  (2023-10-13T17:59:38Z)
• Advancing Visual Grounding with Scene Knowledge: Benchmark and Method [74.72663425217522]
  Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Most existing VG datasets are constructed using simple description texts. We propose a novel benchmark of underlineScene underlineKnowledge-guided underlineVisual underlineGrounding.
  arXiv  Detail & Related papers  (2023-07-21T13:06:02Z)
• Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation [54.419401869108846]
  We propose a single-stage WeaklySupervised Semantic (WSSS) model with only the image-level class label supervisions. A flexible context aggregation module is proposed to capture the global object context in different granular spaces. A semantically consistent feature fusion module is proposed in a bottom-up parameter-learnable fashion to aggregate the fine-grained local contents.
  arXiv  Detail & Related papers  (2023-04-18T15:29:23Z)
• LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval [3.6570455823407957]
  Video-text retrieval is a class of cross-modal representation learning problems. We present a novel mechanism for learning the translation relationship from a source modality space $mathcalS$ to a target modality space $mathcalT$ without the need for a joint latent space.
  arXiv  Detail & Related papers  (2022-07-11T13:37:32Z)
• BOSS: Bottom-up Cross-modal Semantic Composition with Hybrid Counterfactual Training for Robust Content-based Image Retrieval [61.803481264081036]
  Content-Based Image Retrieval (CIR) aims to search for a target image by concurrently comprehending the composition of an example image and a complementary text. We tackle this task by a novel underlinetextbfBottom-up crunderlinetextbfOss-modal underlinetextbfSemantic compounderlinetextbfSition (textbfBOSS) with Hybrid Counterfactual Training framework.
  arXiv  Detail & Related papers  (2022-07-09T07:14:44Z)

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.