Papers › Flash-VStream: Efficient Real-Time Understanding for Long Video Streams

Flash-VStream: Efficient Real-Time Understanding for Long Video Streams

30 Jun 2025arXiv:2506.23825archive 2025-07-28

Haoji Zhang, Yiqin Wang, Yansong Tang, Yong liu, Jiashi Feng, Xiaojie Jin

Benefiting from the advances in large language models and cross-modal alignment, existing multimodal large language models have achieved prominent performance in image and short video understanding. However, the understanding of long videos is still challenging, as their long-context nature results in significant computational and memory overhead. Most existing work treats long videos in the same way as short videos, which is inefficient for real-world applications and hard to generalize to even longer videos. To address these issues, we propose Flash-VStream, an efficient video language model capable of processing extremely long videos and responding to user queries in real time. Particularly, we design a Flash Memory module, containing a low-capacity context memory to aggregate long-context temporal information and model the distribution of information density, and a high-capacity augmentation memory to retrieve detailed spatial information based on this distribution. Compared to existing models, Flash-VStream achieves significant reductions in inference latency. Extensive experiments on long video benchmarks and comprehensive video benchmarks, i.e., EgoSchema, MLVU, LVBench, MVBench and Video-MME, demonstrate the state-of-the-art performance and outstanding efficiency of our method. Code is available at https://github.com/IVGSZ/Flash-VStream.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2506.23825")

Code

Syntology Ran 7 of 11 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

IVGSZ/Flash-VStream officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested; 7 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

7ran
4unverified

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from IVGSZ/Flash-VStream. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

attention_feature IVGSZ/Flash-VStream/Flash-VStream-Qwen/models/vstream_qwen2vl_realtime.py official repository ran Apache-2.0 (permissive) · c522c620944fcbb9 · report
drop_feature IVGSZ/Flash-VStream/Flash-VStream-Qwen/models/vstream_qwen2vl_realtime.py official repository ran fingerprinted Apache-2.0 (permissive) · 88e007251e2c289d · report
fast_weighted_kmeans_ordered_feature IVGSZ/Flash-VStream/Flash-VStream-Qwen/models/vstream_qwen2vl_realtime.py official repository ran fingerprinted Apache-2.0 (permissive) · aeab8c53bd7cc503 · report
merge_feature IVGSZ/Flash-VStream/Flash-VStream-Qwen/models/vstream_qwen2vl_realtime.py official repository ran fingerprinted Apache-2.0 (permissive) · 19b51c02fb81ef10 · report
torchpca_weighted_kmeans_ordered_feature IVGSZ/Flash-VStream/Flash-VStream-Qwen/models/vstream_qwen2vl_realtime.py official repository ran fingerprinted Apache-2.0 (permissive) · 005eab8e2724916d · report
weighted_kmeans_feature IVGSZ/Flash-VStream/Flash-VStream-Qwen/models/vstream_qwen2vl_realtime.py official repository ran fingerprinted Apache-2.0 (permissive) · ae3ae26a8f618992 · report
weighted_kmeans_ordered_feature IVGSZ/Flash-VStream/Flash-VStream-Qwen/models/vstream_qwen2vl_realtime.py official repository ran fingerprinted Apache-2.0 (permissive) · c8be36921dc6305a · report
FlashMemory IVGSZ/Flash-VStream/Flash-VStream-Qwen/models/vstream_qwen2vl_realtime.py official repository unverified Apache-2.0 (permissive) · 5f35f922c5cc5480 · report
dbscan_feature IVGSZ/Flash-VStream/Flash-VStream-Qwen/models/vstream_qwen2vl_realtime.py official repository unverified Apache-2.0 (permissive) · 9c19640a32bf3839 · report
gmm_feature IVGSZ/Flash-VStream/Flash-VStream-Qwen/models/vstream_qwen2vl_realtime.py official repository unverified Apache-2.0 (permissive) · d1517b2bc3b5f27d · report
pca_weighted_kmeans_ordered_feature IVGSZ/Flash-VStream/Flash-VStream-Qwen/models/vstream_qwen2vl_realtime.py official repository unverified Apache-2.0 (permissive) · 9ce5acc98b5b9e0b · report

Tasks

MMEVideo Understandingcross-modal alignment

3 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections