mlsanityData to 14 Oct 2026

Seed1.5-VL Technical Report

arXiv 2505.07062 ↗First posted 11 May 2025cs.CV cs.AIcited by 373

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

also in 1 more
Abstract (arXiv)

We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter vision encoder and a Mixture-of-Experts (MoE) LLM of 20B active parameters. Despite its relatively compact architecture, it delivers strong performance across a wide spectrum of public VLM benchmarks and internal evaluation suites, achieving the state-of-the-art performance on 38 out of 60 public benchmarks. Moreover, in agent-centric tasks such as GUI control and gameplay, Seed1.5-VL outperforms leading multimodal systems, including OpenAI CUA and Claude 3.7. Beyond visual and video understanding, it also demonstrates strong reasoning abilities, making it particularly effective for multimodal reasoning challenges such as visual puzzles. We believe these capabilities will empower broader applications across diverse tasks. In this report, we mainly provide a comprehensive review of our experiences in building Seed1.5-VL across model design, data construction, and training at various stages, hoping that this report can inspire further research. Seed1.5-VL is now accessible at https://www.volcengine.com/ (Volcano Engine Model ID: doubao-1-5-thinking-vision-pro-250428)

Key facts. Cited by 373 papers in the map (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. First posted on arXiv 11 May 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 171; 2026: 202.

373 papers.

Sort:

By area:

  1. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,510
  2. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learningcited by 466
  3. 2025DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learningcited by 410
  4. 2025Seedream 4.0: Toward Next-generation Multimodal Image Generationcited by 249
  5. 2025LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Trainingcited by 244
  6. 2025Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontierscited by 199
  7. 2025MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligencecited by 183
  8. 2025Thyme: Think Beyond Imagescited by 167
  9. 2025OpenCUA: Open Foundations for Computer-Use Agentscited by 160
  10. 2026Seedance 2.0: Advancing Video Generation for World Complexitycited by 160
  11. 2025Scaling Computer-Use Grounding via User Interface Decomposition and Synthesiscited by 139
  12. 2025Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Modelscited by 138
38 more
  1. 2025GR-3 Technical Reportcited by 111
  2. 2025GTA1: GUI Test-time Scaling Agentcited by 106
  3. 2025UI-Venus Technical Report: Building High-performance UI Agents with RFTcited by 93
  4. 2025Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluationcited by 92
  5. 2025MAI-UI Technical Report: Real-World Centric Foundation GUI Agentscited by 91
  6. 2025Visual Spatial Tuningcited by 89
  7. 2025Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learningcited by 87
  8. 2025Scaling Spatial Intelligence with Multimodal Foundation Modelscited by 82
  9. 2025VGR: Visual Grounded Reasoningcited by 73
  10. 2025Kwai Keye-VL 1.5 Technical Reportcited by 73
  11. 2025Detect Anything via Next Point Predictioncited by 73
  12. 2025Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodologycited by 69
  13. 2025ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Datacited by 60
  14. 2025SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learningcited by 57
  15. 2025OneThinker: All-in-one Reasoning Model for Image and Videocited by 56
  16. 2025Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learningcited by 53
  17. 2025OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editingcited by 53
  18. 2025TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMscited by 50
  19. 2025MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoningcited by 49
  20. 2025Kwai Keye-VL Technical Reportcited by 47
  21. 2025dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Modelcited by 47
  22. 2025How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspectivecited by 43
  23. 2025Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmarkcited by 43
  24. 2025Omni-Video: Democratizing Unified Video Understanding and Generationcited by 40
  25. 2025Step-GUI Technical Reportcited by 39
  26. 2025Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoningcited by 34
  27. 2025Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoningcited by 34
  28. 2025MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMscited by 33
  29. 2025MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMscited by 33
  30. 2026Rethinking Video Generation Model for the Embodied Worldcited by 33
  31. 2025Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedbackcited by 32
  32. 2025We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoningcited by 32
  33. 2026STEP3-VL-10B Technical Reportcited by 32
  34. 2025DepthLM: Metric Depth From Vision Language Modelscited by 30
  35. 2025dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thoughtcited by 30
  36. 2025Holistic Evaluation of Multimodal LLMs on Spatial Intelligencecited by 29
  37. 2025InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialoguecited by 29
  38. 2025OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agentscited by 29

50 most cited of 373 All 373 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model
  2. 2024NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision
  3. 2025VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs
  4. 2024DeepSeek-VL: Towards Real-World Vision-Language Understanding
  5. 2024DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
  6. 2026UVLM: A Universal Vision-Language Model Loader for Reproducible Multimodal Benchmarking
  7. 2026V-Zero: Self-Improving Multimodal Reasoning with Zero Annotation
  8. 2025ImageNet-Think-250K: A Large-Scale Synthetic Dataset for Multimodal Reasoning for Vision Language Models