This is the official implementation of ICCV 2025 "Flash-VStream: Efficient Real-Time Understanding for Long Video Streams"
☆274Oct 15, 2025Updated 5 months ago
Alternatives and similar repositories for Flash-VStream
Users that are interested in Flash-VStream are comparing it to the libraries listed below
Sorting:
- VideoLLM-online: Online Video Large Language Model for Streaming Video (CVPR 2024)☆646Nov 26, 2025Updated 3 months ago
- [CVPR 2024] Narrative Action Evaluation with Prompt-Guided Multimodal Interaction☆42May 16, 2024Updated last year
- Official repo for "Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge" ICLR2025☆101Mar 14, 2025Updated last year
- [ICLR'25] Streaming Video Question-Answering with In-context Video KV-Cache Retrieval☆107Nov 4, 2025Updated 4 months ago
- [CVPR 2025] OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?☆125Jul 24, 2025Updated 7 months ago
- ☆23May 9, 2024Updated last year
- [ACM MM 2025] TimeChat-online: 80% Visual Tokens are Naturally Redundant in Streaming Videos☆120Dec 12, 2025Updated 3 months ago
- The official code of "Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning"☆87Oct 15, 2025Updated 5 months ago
- [CVPR'2022, TPAMI'2024] LAVT: Language-Aware Vision Transformer for Referring Segmentation☆24Jan 21, 2025Updated last year
- [CVPR 2025]Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction☆168Mar 23, 2025Updated 11 months ago
- [CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".☆203Jun 18, 2025Updated 9 months ago
- [CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding☆689Jan 29, 2025Updated last year
- [TIP 2025] Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation☆66Dec 22, 2025Updated 2 months ago
- Long Context Transfer from Language to Vision☆402Mar 18, 2025Updated last year
- [ICCV 2025] Official Repository of VideoLLaMB: Long Video Understanding with Recurrent Memory Bridges☆84Feb 27, 2025Updated last year
- [CVPR 2024] The repository contains the official implementation of "Open-Vocabulary Segmentation with Semantic-Assisted Calibration"☆76Sep 23, 2024Updated last year
- [ICML 2025] Official PyTorch implementation of LongVU☆424May 8, 2025Updated 10 months ago
- A lightweight flexible Video-MLLM developed by TencentQQ Multimedia Research Team.☆74Oct 14, 2024Updated last year
- Official PyTorch code of GroundVQA (CVPR'24)☆64Sep 13, 2024Updated last year
- Chat about anything on any video!☆39Sep 5, 2023Updated 2 years ago
- (2024CVPR) MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding☆347Jul 19, 2024Updated last year
- Official implementation of paper VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interact…☆43Feb 5, 2025Updated last year
- ☆51Aug 22, 2025Updated 6 months ago
- ☆17Feb 26, 2024Updated 2 years ago
- LinVT: Empower Your Image-level Large Language Model to Understand Videos☆84Dec 30, 2024Updated last year
- StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding☆150May 16, 2025Updated 10 months ago
- 🔥🔥MLVU: Multi-task Long Video Understanding Benchmark☆242Aug 21, 2025Updated 6 months ago
- [ICLR2026] VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling☆511Nov 18, 2025Updated 4 months ago
- Official repository for the paper PLLaVA☆676Jul 28, 2024Updated last year
- SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models☆289Sep 16, 2024Updated last year
- (ICCV2025) Official repository of paper "ViSpeak: Visual Instruction Feedback in Streaming Videos"☆46Jul 1, 2025Updated 8 months ago
- [ICCV'25] HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics☆38Sep 10, 2025Updated 6 months ago
- 🔥🔥First-ever hour scale video understanding models☆615Jul 14, 2025Updated 8 months ago
- [AAAI 2025] Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos☆33May 27, 2025Updated 9 months ago
- [ICLR 2025] MLLM for On-Demand Spatial-Temporal Understanding at Arbitrary Resolution☆330Jul 4, 2025Updated 8 months ago
- ☆37Sep 16, 2024Updated last year
- [ECCV2024] Official code implementation of Merlin: Empowering Multimodal LLMs with Foresight Minds☆96Jul 4, 2024Updated last year
- ☆157Oct 31, 2024Updated last year
- [ICCV2025] AnyBimanual: Transfering Unimanual Policy for General Bimanual Manipulation☆99Jun 26, 2025Updated 8 months ago