mlsanityData to 14 Oct 2026

FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding

arXiv 2603.02096 ↗First posted 2 Mar 2026cs.CV cs.AIcited by 28

Not on the map. Why?

Abstract (arXiv)

This paper presents FluxMem, a training-free framework for efficient streaming video understanding. FluxMem adaptively compresses redundant visual memory through a hierarchical, two-stage design: (1) a Temporal Adjacency Selection (TAS) module removes redundant visual tokens across adjacent frames, and (2) a Spatial Domain Consolidation (SDC) module further merges spatially repetitive regions within each frame into compact representations. To adapt effectively to dynamic scenes, we introduce a self-adaptive token compression mechanism in both TAS and SDC, which automatically determines the compression rate based on intrinsic scene statistics rather than manual tuning. Extensive experiments demonstrate that FluxMem achieves new state-of-the-art results on existing online video benchmarks, reaching 76.4 on StreamingBench and 67.2 on OVO-Bench under real-time settings, while reducing latency by 69.9% and peak GPU memory by 34.5% on OVO-Bench. Furthermore, it maintains strong offline performance, achieving 73.1 on MLVU while using 65% fewer visual tokens.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 62 of its 67 references that are in the map. First posted on arXiv 2 Mar 2026.

Builds on

62 of 67 references.

References · 62

  1. 2025Qwen2.5-VL Technical Reportcited by 5,587
  2. 2024GPT-4o System Cardcited by 4,588
  3. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  4. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  5. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  6. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,510
  7. 2023Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understandingcited by 1,471
  8. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,413
  9. 2023Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Modelscited by 1,062
  10. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,050
  11. 2022Token Merging: Your ViT But Fastercited by 1,021
  12. 2024LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understandingcited by 665
38 more
  1. 2024An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Modelscited by 642
  2. 2024LLaVA-Video: Video Instruction Tuning With Synthetic Datacited by 583
  3. 2023LLaMA-VID: An Image is Worth 2 Tokens in Large Language Modelscited by 546
  4. 2023MovieChat: From Dense Token to Sparse Memory for Long Video Understandingcited by 542
  5. 2024Long Context Transfer from Language to Visioncited by 515
  6. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  7. 2021Less is More: ClipBERT for Video-and-Language Learning via Sparse Samplingcited by 484
  8. 2023TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understandingcited by 406
  9. 2023Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understandingcited by 371
  10. 2024LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understandingcited by 356
  11. 2024VisionZip: Longer is Better but Not Necessary in Vision Language Modelscited by 313
  12. 2024MLVU: Benchmarking Multi-task Long Video Understandingcited by 292
  13. 2024MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understandingcited by 229
  14. 2024VideoLLM-online: Online Video Large Language Model for Streaming Videocited by 225
  15. 2024Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understandingcited by 213
  16. 2025InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modelingcited by 211
  17. 2023Video Understanding with Large Language Models: A Surveycited by 206
  18. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 179
  19. 2024Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streamscited by 169
  20. 2024Streaming Long Video Understanding with Large Language Modelscited by 167
  21. 2025Adaptive Keyframe Sampling for Long Video Understandingcited by 167
  22. 2024LongVLM: Efficient Long Video Understanding via Large Language Modelscited by 147
  23. 2023To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuningcited by 144
  24. 2024StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understandingcited by 144
  25. 2022OmniVL:One Foundation Model for Image-Language and Video-Language Taskscited by 143
  26. 2025OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?cited by 142
  27. 2025Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reactioncited by 127
  28. 2025Streaming Video Question-Answering with In-context Video KV-Cache Retrievalcited by 117
  29. 2025TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videoscited by 97
  30. 2024DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Modelscited by 96
  31. 2025StreamingVLM: Real-Time Understanding for Infinite Video Streamscited by 95
  32. 2025StreamForest: Efficient Online Video Understanding with Persistent Event Memorycited by 78
  33. 2024MovieChat+: Question-aware Sparse Memory for Long Video Question Answeringcited by 73
  34. 2025Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledgecited by 73
  35. 2024PruneVid: Visual Token Pruning for Efficient Video Large Language Modelscited by 67
  36. 2023ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding Systemcited by 65
  37. 2025StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistantcited by 63
  38. 2024Online Video Understanding: OVBench and VideoChat-Onlinecited by 61

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 28.

28 papers.

Sort:

By area:

  1. 2026A Simple Baseline for Streaming Video Understandingcited by 33
  2. 2026MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memorycited by 14
  3. 2026Semantic-Aware Adaptive Visual Memory for Streaming Video Understandingcited by 8
  4. 2026What Should a Streaming Video Model Remember?cited by 7
  5. 2026OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMscited by 6
  6. 2026ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understandingcited by 5
  7. 2026StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMscited by 5
  8. 2026An Efficient Streaming Video Understanding Framework with Agentic Controlcited by 4
  9. 2026Harnessing Streaming Video in the Wildcited by 4
  10. 2026Towards a Dynamic and Fixed-budget Memory Bank for Efficient Streaming Video Understandingcited by 4
  11. 2026FOLIO: Focused Semantic Memory for Streaming Video Understandingcited by 4
  12. 2026Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrievalcited by 3
16 more
  1. 2026StreamScout: Learning When to Look Deeper for Streaming Video Understandingcited by 3
  2. 2026VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Modelscited by 2
  3. 2026Homer: Understanding Long-form Videos with Hierarchical Memory and Agentic Reasoningcited by 2
  4. 2026How Well Can Your Video Model Remember? Measuring Memory-Budget Trade-offs in Long Video Understandingcited by 1
  5. 2026Think in Sets for Streaming Video Token Compressioncited by 1
  6. 2026StreamFlow: Dynamic Memory Flows for Streaming Video Understandingcited by 1
  7. 2026Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understandingcited by 1
  8. 2026OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interactioncited by 1
  9. 2026Companion-style QA Assistance in Ego-Visioncited by 0
  10. 2026KeyRec: Bounded Visual Memory for Streaming and Long-Video Understandingcited by 0
  11. 2026MemEvo: Automatic Discovery of Streaming Video Memory Mechanismscited by 0
  12. 2026EGSD: Event-Grounded Self-Distillation for Streaming Video Understandingcited by 0
  13. 2026When to Retrieve, When to Stay: Uncertainty-Aware Temporal Evidence Allocation for Streaming Video-LLMscited by 0
  14. 2026APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistantscited by 0
  15. 2026FlashGaze: Training-Free Multi-Scale Patch Pruning For Efficient Video Understandingcited by 0
  16. 2026SPARE: Shared Perception and Adaptive Retrieval of Evidence for Streaming Video Understandingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025StreamingTOM: Streaming Token Compression for Efficient Video Understanding
  2. 2026CoRDS: Coreset-based Representative and Diverse Selection for Streaming Video Understanding
  3. 2026ReMem: Streaming Video Understanding With Long Context Retention
  4. 2026Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory
  5. 2026StreamEMS: Streaming Video Understanding with Self-Evolving Memory Scheme for Vision-Language Models
  6. 2026HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
  7. 2026MEMO: Multi-Level Entity-Aware Memory for Streaming Video Understanding
  8. 2026ProtoKV: Streaming Video Understanding under Delayed Query with Summary-State Memory