DeepThinkVLA
by OpenBMB · GitHub
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
⭐ Stars
527
🍴 Forks
49
📜 License
MIT
Commercial use OK📅 Created
2025
🔄 Last commit
3 mo ago
🏷️ Category
reasoning-models
💻 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
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
❓ Frequently asked questions
What is DeepThinkVLA?
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
Is DeepThinkVLA open source?
DeepThinkVLA is an open-source project. It is released under the MIT license.
Is DeepThinkVLA free?
Yes. DeepThinkVLA 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.
[](https://opensourceai.tech/project/openbmb-deepthinkvla.html)
🧬 Related projects🧬 View the DNA map →
MiniMax-M1
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
★ 3.2k · large-language-models
LightReasoner
[ACL 2026 Oral] "LightReasoner: Can Small Language Models Teach Large Language Models Reasoning…
★ 602 · large-language-models
dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
★ 10.9k · ai