mlsanityData to 7 Oct 2026

Qwen2.5-VL Technical Report

arXiv 2502.13923 ↗First posted 19 Feb 2025cs.CV cs.CLcited by 5,418

Not on the map. Why?

Cited by 2,302 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities. Qwen2.5-VL achieves a major leap forward in understanding and interacting with the world through enhanced visual recognition, precise object localization, robust document parsing, and long-video comprehension. A standout feature of Qwen2.5-VL is its ability to localize objects using bounding boxes or points accurately. It provides robust structured data extraction from invoices, forms, and tables, as well as detailed analysis of charts, diagrams, and layouts. To handle complex inputs, Qwen2.5-VL introduces dynamic resolution processing and absolute time encoding, enabling it to process images of varying sizes and videos of extended durations (up to hours) with second-level event localization. This allows the model to natively perceive spatial scales and temporal dynamics without relying on traditional normalization techniques. By training a native dynamic-resolution Vision Transformer (ViT) from scratch and incorporating Window Attention, we reduce computational overhead while maintaining native resolution. As a result, Qwen2.5-VL excels not only in static image and document understanding but also as an interactive visual agent capable of reasoning, tool usage, and task execution in real-world scenarios such as operating computers and mobile devices. Qwen2.5-VL is available in three sizes, addressing diverse use cases from edge AI to high-performance computing. The flagship Qwen2.5-VL-72B model matches state-of-the-art models like GPT-4o and Claude 3.5 Sonnet, particularly excelling in document and diagram understanding. Additionally, Qwen2.5-VL maintains robust linguistic performance, preserving the core language competencies of the Qwen2.5 LLM.

Key facts. Cited by 5,418 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Feb 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2713; 2026: 2705.

5,418 papers.

Sort:

By area:

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  3. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  4. 2025Qwen-Image Technical Reportcited by 973
  5. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 948
  6. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  7. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
  8. 2025Qwen2.5-Omni Technical Reportcited by 704
  9. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 653
  10. 2025Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoningcited by 540
  11. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Modelcited by 515
  12. 2025Video-R1: Reinforcing Video Reasoning in MLLMscited by 464
38 more
  1. 2025Qwen3-Omni Technical Reportcited by 451
  2. 2025Group-in-Group Policy Optimization for LLM Agent Trainingcited by 442
  3. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learningcited by 439
  4. 2025Step1X-Edit: A Practical Framework for General Image Editingcited by 417
  5. 2025DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learningcited by 398
  6. 2025Kimi-VL Technical Reportcited by 381
  7. 2025R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalizationcited by 364
  8. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 351
  9. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  10. 2025VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learningcited by 315
  11. 2025R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimizationcited by 296
  12. 2025VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulnesscited by 289
  13. 2025Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learningcited by 267
  14. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuningcited by 252
  15. 2025VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuningcited by 248
  16. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 247
  17. 2025LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RLcited by 244
  18. 2025Show-o2: Improved Native Unified Multimodal Modelscited by 242
  19. 2025OmniGen2: Towards Instruction-Aligned Multimodal Generationcited by 241
  20. 2025GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agentscited by 240
  21. 2025Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcementcited by 234
  22. 2025LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Trainingcited by 233
  23. 2025Transfer between Modalities with MetaQueriescited by 231
  24. 2025Motus: A Unified Latent Action World Modelcited by 231
  25. 2025ImgEdit: A Unified Image Editing Dataset and Benchmarkcited by 225
  26. 2025SkyReels-V2: Infinite-length Film Generative Modelcited by 218
  27. 2025Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoningcited by 217
  28. 2025Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligencecited by 206
  29. 2025In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformercited by 199
  30. 2025Unified Reward Model for Multimodal Understanding and Generationcited by 194
  31. 2025Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontierscited by 193
  32. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Drivingcited by 190
  33. 2025Mobile-Agent-v3: Fundamental Agents for GUI Automationcited by 183
  34. 2025World Simulation with Video Foundation Models for Physical AIcited by 183
  35. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  36. 2025DeepSeek-OCR: Contexts Optical Compressioncited by 174
  37. 2025MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligencecited by 169
  38. 2025DreamGen: Unlocking Generalization in Robot Learning through Video World Modelscited by 168

50 most cited of 5,418 All 5,418 (JSON)