VisionReasoner
[ICLR 2026] VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
Explore advanced visual tasks using a unified AI model that integrates reasoning and perception.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytime[ICLR 2026] VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
VisionReasoner has 348 stars on GitHub. It has been forked 15 times. VisionReasoner is written mainly in Python. It has been in active development since 2025. VisionReasoner is available under the Apache-2.0 license. Its main topics are counting-objects, multimodal, multimodal-large-language-models, object-detection.
What is VisionReasoner?
[ICLR 2026] VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
Is VisionReasoner open source?
VisionReasoner is an open-source project. It is released under the Apache-2.0 license.
Is VisionReasoner free?
Yes. VisionReasoner is free and open source — you can use, modify and self-host it.
What license does VisionReasoner use?
VisionReasoner is available under the Apache-2.0 license.
What language is VisionReasoner written in?
VisionReasoner is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/jia-lab-research-visionreasoner.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.