mlsanityData to 14 Oct 2026

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

arXiv 2504.15271 ↗First posted 21 Apr 2025cs.CVcited by 64

On the map: Multimodal LLMs / vision-language models → Video understanding with MLLMs

Abstract (arXiv)

We introduce Eagle 2.5, a family of frontier vision-language models (VLMs) for long-context multimodal learning. Our work addresses the challenges in long video comprehension and high-resolution image understanding, introducing a generalist framework for both tasks. The proposed training framework incorporates Automatic Degrade Sampling and Image Area Preservation, two techniques that preserve contextual integrity and visual details. The framework also includes numerous efficiency optimizations in the pipeline for long-context data training. Finally, we propose Eagle-Video-110K, a novel dataset that integrates both story-level and clip-level annotations, facilitating long-video understanding. Eagle 2.5 demonstrates substantial improvements on long-context multimodal benchmarks, providing a robust solution to the limitations of existing VLMs. Notably, our best model Eagle 2.5-8B achieves 72.4% on Video-MME with 512 input frames, matching the results of top-tier commercial model such as GPT-4o and large-scale open-source models like Qwen2.5-VL-72B and InternVL2.5-78B.

Key facts. Cited by 64 papers in the map (data through 14 Oct 2026). Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 101 of its 124 references that are in the map. First posted on arXiv 21 Apr 2025.

Builds on

101 of 124 references.

Closest ancestors · 12

Same direction, newest first

  1. 2025Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy7 Feb
  2. 2024VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling31 Dec
  3. 2024CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding16 Dec
  4. 2024LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding22 Oct
  5. 2024LongVILA: Scaling Long-Context Visual Language Models for Long Videos19 Aug
  6. 2024LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding22 Jul
  7. 2024Long Context Transfer from Language to Vision24 Jun
  8. 2024Long Story Short: Story-level Video Understanding from 20K Short Films14 Jun
  9. 2024VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding13 Jun
  10. 2024LITA: Language Instructed Temporal-Localization Assistant27 Mar
  11. 2023LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models28 Nov
  12. 2023MVBench: A Comprehensive Multi-modal Video Understanding Benchmark28 Nov

Other references · 89

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  5. 2025Qwen2.5-VL Technical Reportcited by 5,587
  6. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  7. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  8. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  9. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  10. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  11. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  12. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
38 more
  1. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  2. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  3. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  4. 2019Towards VQA Models That Can Readcited by 1,718
  5. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,614
  6. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  7. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  8. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,479
  9. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  10. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
  11. 2021Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrievalcited by 1,177
  12. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,103
  13. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  14. 2019HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clipscited by 950
  15. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?cited by 914
  16. 2023VideoChat: Chat-Centric Video Understandingcited by 857
  17. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 838
  18. 2021NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actionscited by 744
  19. 2017Towards Automatic Learning of Procedures from Web Instructional Videoscited by 619
  20. 2017TALL: Temporal Activity Localization via Language Querycited by 584
  21. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 583
  22. 2023MovieChat: From Dense Token to Sparse Memory for Long Video Understandingcited by 542
  23. 2023InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generationcited by 497
  24. 2019CLEVRER: CoLlision Events for Video REpresentation and Reasoningcited by 484
  25. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 476
  26. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 475
  27. 2018TVQA: Localized, Compositional Video Question Answeringcited by 467
  28. 2021InfographicVQAcited by 437
  29. 2024Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teacherscited by 393
  30. 2024ShareGPT4Video: Improving Video Understanding and Generation with Better Captionscited by 388
  31. 2023Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understandingcited by 371
  32. 2019COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysiscited by 318
  33. 2023Perception Test: A Diagnostic Benchmark for Multimodal Video Modelscited by 314
  34. 2024STAR: A Benchmark for Situated Reasoning in Real-World Videoscited by 213
  35. 2024NVILA: Efficient Frontier Visual Language Modelscited by 209
  36. 2020MovieNet: A Holistic Dataset for Movie Understandingcited by 206
  37. 2023Self-Chained Image-Language Model for Video Localization and Question Answeringcited by 203
  38. 2023SlideVQA: A Dataset for Document Visual Question Answering on Multiple Imagescited by 179

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 27; 2026: 37.

64 papers.

Sort:

By area:

  1. 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planningcited by 156
  2. 2025OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLMcited by 59
  3. 2026InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulationcited by 50
  4. 2025Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsificationcited by 37
  5. 2025ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Contextcited by 35
  6. 2025Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spacescited by 33
  7. 2025VideoITG: Multimodal Video Understanding with Instructed Temporal Groundingcited by 29
  8. 2026RLDX-1 Technical Reportcited by 28
  9. 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 28
  10. 2025Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Modelcited by 27
  11. 2025Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoningcited by 26
  12. 2025ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesiscited by 26
38 more
  1. 2026Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planningcited by 24
  2. 2025Contrastive Representation Regularization for Vision-Language-Action Modelscited by 17
  3. 2026SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoningcited by 17
  4. 2025AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMscited by 16
  5. 2025EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoTcited by 16
  6. 2025π_textttRL: Online RL Fine-tuning for Flow-based Vision-Language-Action Modelscited by 16
  7. 2025Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Followingcited by 15
  8. 2026MolmoPoint: Better Pointing for VLMs with Grounding Tokenscited by 15
  9. 2025Understanding Language Prior of LVLMs by Contrasting Chain-of-Embeddingcited by 14
  10. 2025Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Modelscited by 14
  11. 2025Exploring Diffusion Transformer Designs via Graftingcited by 12
  12. 2025ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learningcited by 10
  13. 2026Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document Retrievalcited by 10
  14. 2026PhyCritic: Multimodal Critic Models for Physical AIcited by 10
  15. 2026VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understandingcited by 10
  16. 2026AgentVLN: Towards Agentic Vision-and-Language Navigationcited by 9
  17. 2025Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculationcited by 8
  18. 2026Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baselinecited by 8
  19. 2026OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulationcited by 8
  20. 2025VFaith: Do Large Multimodal Models Really Reason on Seen Images Rather than Previous Memories?cited by 7
  21. 2025UniComp: Rethinking Video Compression Through Informational Uniquenesscited by 7
  22. 2026AdaCodec: A Predictive Visual Code for Video MLLMscited by 7
  23. 2025SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learningcited by 6
  24. 2025FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videoscited by 5
  25. 2026Safe-Night VLA: Seeing the Unseen via Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulationcited by 5
  26. 2026One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understandingcited by 5
  27. 2026Cambrian-P: Pose-Grounded Video Understandingcited by 5
  28. 2025PRISM-Bench: A Benchmark of Puzzle-Based Visual Tasks with CoT Error Detectioncited by 4
  29. 2026WarmPrior: Straightening Flow-Matching Policies with Temporal Priorscited by 4
  30. 2026VISTAQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidencecited by 4
  31. 2026Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMscited by 4
  32. 2026VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detectioncited by 3
  33. 2026Video-Oasis: Rethinking Evaluation of Video Understandingcited by 3
  34. 2026Modular Sensory Stream for Integrating Physical Feedback in Vision-Language-Action Modelscited by 3
  35. 2026Beyond a Single Frame: Multi-Frame Spatially Grounded Reasoning Across Volumetric MRIcited by 2
  36. 2025SA-Person: Text-Based Person Retrieval with Scene-aware Re-rankingcited by 1
  37. 2026STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Modelscited by 1
  38. 2026Linear Scaling Video VLMs for Long Video Understandingcited by 1

50 most cited of 64 All 64 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Visual Context Window Extension: A New Perspective for Long Video Understanding
  2. 2026Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
  3. 2024From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding
  4. 2024Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models
  5. 2025MMLongCite: A Benchmark for Evaluating Fidelity of Long-Context Vision-Language Models
  6. 2024InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
  7. 2025Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models
  8. 2025InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling