mlsanityData to 14 Oct 2026

Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought

arXiv 2504.05599 ↗First posted 8 Apr 2025cs.CV cs.CLcited by 69

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

We introduce Skywork R1V, a multimodal reasoning model extending the an R1-series Large language models (LLM) to visual modalities via an efficient multimodal transfer method. Leveraging a lightweight visual projector, Skywork R1V facilitates seamless multimodal adaptation without necessitating retraining of either the foundational language model or the vision encoder. To strengthen visual-text alignment, we propose a hybrid optimization strategy that combines Iterative Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), significantly enhancing cross-modal integration efficiency. Additionally, we introduce an adaptive-length Chain-of-Thought distillation approach for reasoning data generation. This approach dynamically optimizes reasoning chain lengths, thereby enhancing inference efficiency and preventing excessive reasoning overthinking. Empirical evaluations demonstrate that Skywork R1V, with only 38B parameters, delivers competitive performance, achieving a score of 69.0 on the MMMU benchmark and 67.5 on MathVista. Meanwhile, it maintains robust textual reasoning performance, evidenced by impressive scores of 72.0 on AIME and 94.0 on MATH500. The Skywork R1V model weights have been publicly released to promote openness and reproducibility.

Key facts. Cited by 69 papers in the map (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 13 of its 17 references that are in the map. First posted on arXiv 8 Apr 2025.

Builds on

13 of 17 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling6 Dec
  2. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts3 Oct

Other references · 11

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2025Qwen2.5-VL Technical Reportcited by 5,587
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  7. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  8. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  9. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  10. 2023VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Taskscited by 501
  11. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 248

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 45; 2026: 24.

69 papers.

Sort:

By area:

  1. 2025Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawingcited by 136
  2. 2025R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPOcited by 52
  3. 2025Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoningcited by 49
  4. 2025Advancing Multimodal Reasoning via Reinforcement Learning with Cold Startcited by 41
  5. 2025First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Trainingcited by 34
  6. 2025Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoningcited by 34
  7. 2025Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoningcited by 33
  8. 2025Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoningcited by 32
  9. 2025SurgVLM: A Large Vision-Language Model and Systematic Evaluation Benchmark for Surgical Intelligencecited by 31
  10. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMscited by 31
  11. 2025More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Modelscited by 27
  12. 2025EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewardscited by 27
38 more
  1. 2025Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearchcited by 27
  2. 2025Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoningcited by 26
  3. 2025VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoningcited by 26
  4. 2025A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Modelscited by 25
  5. 2025ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Mapscited by 23
  6. 2026VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twicecited by 21
  7. 2025Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsingcited by 17
  8. 2025Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Modelscited by 16
  9. 2025GThinker: Towards General Multimodal Reasoning via Cue-Guided Rethinkingcited by 15
  10. 2025Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Modelscited by 14
  11. 2025SiLVR: A Simple Language-based Video Reasoning Frameworkcited by 14
  12. 2025VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Taskscited by 14
  13. 2025MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGIcited by 14
  14. 2025High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learningcited by 14
  15. 2025Sherlock: Self-Correcting Reasoning in Vision-Language Modelscited by 13
  16. 2025ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State Representationscited by 12
  17. 2025The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMscited by 12
  18. 2025Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learningcited by 11
  19. 2025AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoningcited by 11
  20. 2025Can GRPO Boost Complex Multimodal Table Understanding?cited by 10
  21. 2025OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoningcited by 10
  22. 2025APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimizationcited by 9
  23. 2025MiCo: Multi-image Contrast for Reinforcement Visual Reasoningcited by 9
  24. 2025Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM Perceptioncited by 9
  25. 2025BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perceptioncited by 9
  26. 2026MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoningcited by 9
  27. 2026Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMscited by 9
  28. 2025SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoningcited by 8
  29. 2026CoVR-R:Reason-Aware Composed Video Retrievalcited by 8
  30. 2026Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled Preference Optimizationcited by 7
  31. 2025MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Modelscited by 6
  32. 2026Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Modelscited by 6
  33. 2025ReLaX: Reasoning with Latent Exploration for Large Reasoning Modelscited by 5
  34. 2026RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoningcited by 5
  35. 2026S1-VL: Scientific Multimodal Reasoning Model with Thinking-with-Imagescited by 5
  36. 2026CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentratingcited by 5
  37. 2026Learning Self-Correction in Vision-Language Models via Rollout Augmentationcited by 4
  38. 2025Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsingcited by 3

50 most cited of 69 All 69 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
  2. 2025AStar: Boosting Multimodal Reasoning with Automated Structured Thinking
  3. 2026Adaptive Look, Flexible Thought: Learning How and How Long to Think in Multimodal Reasoning
  4. 2026Distilling Visual Reasoning into Text Space
  5. 2026TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding
  6. 2026CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions
  7. 2026AdaptMMBench: Benchmarking Adaptive Multimodal Reasoning for Mode Selection and Reasoning Process
  8. 2026DeltaV: Thinking with Visual State Updates in Unified Large Multimodal Models