Shadowgraph
TrendingAbout
Sign in

zhang9302002/Flash-VStream-Qwen-7b

Model

Flash-VStream-Qwen-7b Model Card

1

4 commits

1 linked in READMEs

updated Oct 15, 2025

See the code

README

Flash-VStream-Qwen-7b Model Card

Model details

We proposed Flash-VStream, an efficient VLM with a novel Flash Memory mechanism that enables real-time understanding and Q&A of extremely long video streams. Our model achieves outstanding accuracy and efficiency on EgoSchema, MLVU, LVBench, MVBench and Video-MME Benchmarks.

License

This project is licensed under the Apache 2.0 License.

flash_vstream_qwen2_vl
qwen2vl
safetensors
video understanding
vision-language model

Similar repos

Catalan258/VST-7B

Model

VST-7B

1

DAMO-NLP-SG/VideoRefer-7B

Model

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM

5

orange-sk/ViLAMP-llava-qwen_sig

Model

ViLAMP-llava-qwen

0

Catalan258/VST-3B

Model

VST-3B

2

Catalan258/VST-32B

Model

VST-32B

0

tsinghua-ee/video-SALMONN2_plus_7B_full

Model

Full model for video-SALMONN 2+ 7B.

2

DAMO-NLP-SG/VideoRefer-VideoLLaMA3-7B

Model

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM

13

fushh7/ViSpeak-s2

Model

This repository contains the model of the paper [ViSpeak: Visual Instruction Feedback in Streaming…

0

Linked in READMEs

yaolinli/MLLM-Token-Compression

Towards Efficient Multimodal Large Language Models: A Survey on Token Compression

225

README badge

zhang9302002/Flash-VStream-Qwen-7b

Model

Flash-VStream-Qwen-7b Model Card

1

4 commits

1 linked in READMEs

updated Oct 15, 2025

See the code

README

Flash-VStream-Qwen-7b Model Card

Model details

We proposed Flash-VStream, an efficient VLM with a novel Flash Memory mechanism that enables real-time understanding and Q&A of extremely long video streams. Our model achieves outstanding accuracy and efficiency on EgoSchema, MLVU, LVBench, MVBench and Video-MME Benchmarks.

License

This project is licensed under the Apache 2.0 License.

flash_vstream_qwen2_vl
qwen2vl
safetensors
video understanding
vision-language model

Similar repos

Catalan258/VST-7B

Model

VST-7B

1

DAMO-NLP-SG/VideoRefer-7B

Model

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM

5

orange-sk/ViLAMP-llava-qwen_sig

Model

ViLAMP-llava-qwen

0

Catalan258/VST-3B

Model

VST-3B

2

Catalan258/VST-32B

Model

VST-32B

0

tsinghua-ee/video-SALMONN2_plus_7B_full

Model

Full model for video-SALMONN 2+ 7B.

2

DAMO-NLP-SG/VideoRefer-VideoLLaMA3-7B

Model

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM

13

fushh7/ViSpeak-s2

Model

This repository contains the model of the paper [ViSpeak: Visual Instruction Feedback in Streaming…

0

Linked in READMEs

yaolinli/MLLM-Token-Compression

Towards Efficient Multimodal Large Language Models: A Survey on Token Compression

225

README badge