mlsanityData to 14 Oct 2026

R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

arXiv 2503.10615 ↗First posted 13 Mar 2025cs.CVcited by 370

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

Large Language Models have demonstrated remarkable reasoning capability in complex textual tasks. However, multimodal reasoning, which requires integrating visual and textual information, remains a significant challenge. Existing visual-language models often struggle to effectively analyze and reason visual content, resulting in suboptimal performance on complex reasoning tasks. Moreover, the absence of comprehensive benchmarks hinders the accurate assessment of multimodal reasoning capabilities. In this paper, we introduce R1-Onevision, a multimodal reasoning model designed to bridge the gap between visual perception and deep reasoning. To achieve this, we propose a cross-modal reasoning pipeline that transforms images into formal textural representations, enabling precise language-based reasoning. Leveraging this pipeline, we construct the R1-Onevision dataset which provides detailed, step-by-step multimodal reasoning annotations across diverse domains. We further develop the R1-Onevision model through supervised fine-tuning and reinforcement learning to cultivate advanced reasoning and robust generalization abilities. To comprehensively evaluate multimodal reasoning performance across different grades, we introduce R1-Onevision-Bench, a benchmark aligned with human educational stages, covering exams from junior high school to university and beyond. Experimental results show that R1-Onevision achieves state-of-the-art performance, outperforming models such as GPT-4o and Qwen2.5-VL on multiple challenging multimodal reasoning benchmarks.

Key facts. Cited by 370 papers in the map (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 31 of its 39 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

31 of 39 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs10 Jan
  2. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling6 Dec
  3. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale6 Dec
  4. 2024LLaVA-CoT: Let Vision Language Models Reason Step-by-Step15 Nov
  5. 2024DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models29 Oct
  6. 2024We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?1 Jul
  7. 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset22 Feb
  8. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts3 Oct

Other references · 23

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2025Qwen2.5-VL Technical Reportcited by 5,587
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  7. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  8. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  9. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  10. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  11. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  12. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
11 more
  1. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  2. 2022Towards Reasoning in Large Language Models: A Surveycited by 596
  3. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 586
  4. 2025Humanity's Last Examcited by 491
  5. 2017FigureQA: An Annotated Figure Dataset for Visual Reasoningcited by 319
  6. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 307
  7. 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Executioncited by 300
  8. 2024Large Language Models for Mathematical Reasoning: Progresses and Challengescited by 284
  9. 2019RAVEN: A Dataset for Relational and Analogical Visual rEasoNingcited by 226
  10. 2024Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Searchcited by 175
  11. 2023Cumulative Reasoning with Large Language Modelscited by 94

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 228; 2026: 142.

370 papers.

Sort:

By area:

  1. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,510
  2. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Modelcited by 526
  3. 2025VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learningcited by 323
  4. 2025VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuningcited by 255
  5. 2025SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Modelscited by 212
  6. 2025T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoTcited by 166
  7. 2025SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvementcited by 145
  8. 2025Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawingcited by 136
  9. 2025GRIT: Teaching MLLMs to Think with Imagescited by 125
  10. 2025OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cyclescited by 124
  11. 2025VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Modelscited by 107
  12. 2025Latent Visual Reasoningcited by 104
38 more
  1. 2025Perception-Aware Policy Optimization for Multimodal Reasoningcited by 99
  2. 2025Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMscited by 96
  3. 2025VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuningcited by 93
  4. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 90
  5. 2025SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Modelscited by 90
  6. 2025Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learningcited by 87
  7. 2025NoisyRollout: Reinforcing Visual Reasoning with Data Augmentationcited by 86
  8. 2025More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Modelscited by 86
  9. 2025UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learningcited by 84
  10. 2025Zebra-CoT: A Dataset for Interleaved Vision Language Reasoningcited by 84
  11. 2025VGR: Visual Grounded Reasoningcited by 73
  12. 2025Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoningcited by 68
  13. 2025Ming-Omni: A Unified Multimodal Model for Perception and Generationcited by 66
  14. 2025VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perceptioncited by 65
  15. 2025Safety in Large Reasoning Models: A Surveycited by 64
  16. 2025VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agentscited by 62
  17. 2025DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPOcited by 61
  18. 2025SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learningcited by 57
  19. 2025Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Visioncited by 56
  20. 2025Look-Back: Implicit Visual Re-focusing in MLLM Reasoningcited by 55
  21. 2025Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learningcited by 53
  22. 2025R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPOcited by 52
  23. 2025GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learningcited by 52
  24. 2025Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learningcited by 49
  25. 2025MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoningcited by 49
  26. 2025SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Rewardcited by 45
  27. 2025Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Rewardcited by 45
  28. 2025Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Modelscited by 44
  29. 2025ZeroGUI: Automating Online GUI Learning at Zero Human Costcited by 44
  30. 2025VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learningcited by 43
  31. 2025GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoningcited by 42
  32. 2025Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasonercited by 40
  33. 2025JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agentcited by 39
  34. 2025MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resourcescited by 39
  35. 2025Spotlight on Token Perception for Multimodal Reinforcement Learningcited by 39
  36. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Modelscited by 37
  37. 2025OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipecited by 37
  38. 2025Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoningcited by 36

50 most cited of 370 All 370 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning
  2. 2025ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
  3. 2025Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought
  4. 2025OneThinker: All-in-one Reasoning Model for Image and Video
  5. 2025Mind with Eyes: from Language Reasoning to Multimodal Reasoning
  6. 2026See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs
  7. 2025Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning
  8. 2025Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models