mlsanityData to 7 Oct 2026

Kimi-VL Technical Report

arXiv 2504.07491 ↗First posted 10 Apr 2025cs.CVcited by 381

On the map: LLM reasoning → Multimodal reasoning

also in 2 more
Abstract (arXiv)

We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities - all while activating only 2.8B parameters in its language decoder (Kimi-VL-A3B). Kimi-VL demonstrates strong performance across challenging domains: as a general-purpose VLM, Kimi-VL excels in multi-turn agent tasks (e.g., OSWorld), matching flagship models. Furthermore, it exhibits remarkable capabilities across diverse challenging vision language tasks, including college-level image and video comprehension, OCR, mathematical reasoning, and multi-image understanding. In comparative evaluations, it effectively competes with cutting-edge efficient VLMs such as GPT-4o-mini, Qwen2.5-VL-7B, and Gemma-3-12B-IT, while surpassing GPT-4o in several key domains. Kimi-VL also advances in processing long contexts and perceiving clearly. With a 128K extended context window, Kimi-VL can process diverse long inputs, achieving impressive scores of 64.5 on LongVideoBench and 35.1 on MMLongBench-Doc. Its native-resolution vision encoder, MoonViT, further allows it to see and understand ultra-high-resolution visual inputs, achieving 83.2 on InfoVQA and 34.5 on ScreenSpot-Pro, while maintaining lower computational cost for common tasks. Building upon Kimi-VL, we introduce an advanced long-thinking variant: Kimi-VL-Thinking-2506. Developed through long chain-of-thought (CoT) supervised fine-tuning (SFT) and reinforcement learning (RL), the latest model exhibits strong long-horizon reasoning capabilities (64.0 on MMMU, 46.3 on MMMU-Pro, 56.9 on MathVision, 80.1 on MathVista, 65.2 on VideoMMMU) while obtaining robust general abilities. Code and models are publicly accessible at https://github.com/MoonshotAI/Kimi-VL.

Key facts. Cited by 381 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 52 of its 61 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

52 of 61 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale6 Dec
  2. 2024Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction5 Dec
  3. 2024TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models30 Oct
  4. 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset22 Feb
  5. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts3 Oct
  6. 2023MMBench: Is Your Multi-modal Model an All-around Player?12 Jul

Other references · 46

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  2. 2025Qwen2.5-VL Technical Reportcited by 5,418
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  5. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  6. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  7. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  8. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  9. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  10. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  11. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  12. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,375
34 more
  1. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  2. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,265
  3. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,221
  4. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,193
  5. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
  6. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?cited by 893
  7. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  8. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 822
  9. 2016A Diagram Is Worth A Dozen Imagescited by 793
  10. 2023EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understandingcited by 666
  11. 2024LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understandingcited by 644
  12. 2023DataComp: In search of the next generation of multimodal datasetscited by 635
  13. 2021Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LMcited by 621
  14. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spacescited by 580
  15. 2024DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understandingcited by 559
  16. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agentscited by 553
  17. 2024BLINK: Multimodal Large Language Models Can See but Not Perceivecited by 529
  18. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 483
  19. 2023Ring Attention with Blockwise Transformers for Near-Infinite Contextcited by 448
  20. 2021InfographicVQAcited by 430
  21. 2025Muon is Scalable for LLM Trainingcited by 381
  22. 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agentscited by 370
  23. 2023OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documentscited by 316
  24. 2022Reducing Activation Recomputation in Large Transformer Modelscited by 300
  25. 2025ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Usecited by 246
  26. 2023DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Modelscited by 239
  27. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 226
  28. 2025Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videoscited by 225
  29. 2024Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scalecited by 212
  30. 2023Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Textcited by 208
  31. 2024General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Modelcited by 174
  32. 2024Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Datasetcited by 153
  33. 2024Aria: An Open Multimodal Native Mixture-of-Experts Modelcited by 136
  34. 2025MMVU: Measuring Expert-Level Multi-Discipline Video Understandingcited by 131

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 175; 2026: 206.

381 papers.

Sort:

By area:

  1. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  2. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  3. 2026Kimi K2.5: Visual Agentic Intelligencecited by 449
  4. 2025DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learningcited by 398
  5. 2025OpenCUA: Open Foundations for Computer-Use Agentscited by 151
  6. 2025MMSearch-R1: Incentivizing LMMs to Searchcited by 120
  7. 2025ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Modelscited by 110
  8. 2025Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?cited by 107
  9. 2026Kimi K3: Open Frontier Intelligencecited by 99
  10. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  11. 2025Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoningcited by 88
  12. 2025SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Modelscited by 83
38 more
  1. 2025Flash-VStream: Efficient Real-Time Understanding for Long Video Streamscited by 78
  2. 2025GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agentscited by 73
  3. 2025Kwai Keye-VL 1.5 Technical Reportcited by 68
  4. 2025MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agentscited by 64
  5. 2025Ming-Omni: A Unified Multimodal Model for Perception and Generationcited by 62
  6. 2025ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Datacited by 58
  7. 2025SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learningcited by 53
  8. 2025Kwai Keye-VL Technical Reportcited by 47
  9. 2026Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understandingcited by 46
  10. 2026BabyVision: Visual Reasoning Beyond Languagecited by 39
  11. 2025DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Responsecited by 35
  12. 2025Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoningcited by 34
  13. 2025MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMscited by 31
  14. 2025VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Modelscited by 31
  15. 2025SurgVLM: A Large Vision-Language Model and Systematic Evaluation Benchmark for Surgical Intelligencecited by 30
  16. 2026LongCat-Next: Lexicalizing Modalities as Discrete Tokenscited by 30
  17. 2025Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Informationcited by 27
  18. 2025InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialoguecited by 27
  19. 2025VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoningcited by 26
  20. 2025OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoningcited by 25
  21. 2025VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videoscited by 24
  22. 2025Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoningcited by 23
  23. 2026LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMscited by 22
  24. 2025Visual Autoregressive Modeling for Instruction-Guided Image Editingcited by 21
  25. 2025Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generationcited by 21
  26. 2025OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Modelscited by 21
  27. 2025SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Modelscited by 21
  28. 2025ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Mapscited by 20
  29. 2025RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learningcited by 20
  30. 2026Dolphin-v2: Universal Document Parsing via Scalable Anchor Promptingcited by 20
  31. 2026AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machinescited by 20
  32. 2025SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligencecited by 19
  33. 2025A Survey on Agentic Multimodal Large Language Modelscited by 19
  34. 2025Scaling Language-Centric Omnimodal Representation Learningcited by 19
  35. 2025AirCopBench: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoningcited by 19
  36. 2025Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Modelcited by 18
  37. 2025MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarioscited by 18
  38. 2025AI for Service: Proactive Assistance with AI Glassescited by 18

50 most cited of 381 All 381 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models
  2. 2025VLURes: Benchmarking VLM Visual and Linguistic Understanding in Low-Resource Languages
  3. 2025Seed1.5-VL Technical Report
  4. 2024Heron-Bench: A Benchmark for Evaluating Vision Language Models in Japanese
  5. 2025From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens
  6. 2026Vision Verification Enhanced Fusion of VLMs for Efficient Visual Reasoning
  7. 2024Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of Experts
  8. 2026Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks