Home› Projects› FlashVID

FlashVID

by Fanziyang-v · GitHub

[ICLR 2026 Oral] FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging

# efficiency# flashvid# multimodal# token-compression

⭐ Stars

111

🍴 Forks

🔥 Trending

+1 today

📜 License

MIT

Commercial use OK

📅 Created

2026

🔄 Last commit

2 mo ago

🏷️ Category

efficiency

💻 Language

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

📈 Star history

2026-07-202026-07-21

📄 About

[ICLR 2026 Oral] FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging

❓ Frequently asked questions

[ICLR 2026 Oral] FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging

FlashVID is an open-source project. It is released under the MIT license.

Yes. FlashVID is free and open source — you can use, modify and self-host it.

🏅 Maintainer of this project?

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![OpenSourceAI](https://opensourceai.tech/badge.php?tool=fanziyang-v-flashvid)](https://opensourceai.tech/project/fanziyang-v-flashvid.html)