https://github.com/Deep-Agent/R1-V

Witness the aha moment of VLM with less than $3.
https://github.com/Deep-Agent/R1-V

Last synced: 8 months ago
JSON representation

Witness the aha moment of VLM with less than $3.

• Host: GitHub
• URL: https://github.com/Deep-Agent/R1-V
• Owner: Deep-Agent
• Created: 2025-02-02T18:19:54.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2025-02-02T21:40:33.000Z (8 months ago)
• Last Synced: 2025-02-02T22:26:17.430Z (8 months ago)
• Homepage:
• Size: 1.47 MB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0

Awesome Lists containing this project

• awesome-llm-strawberry - R1-V Team
• Awesome-Large-Multimodal-Reasoning-Models - R1-V - VL | CLEVR , GEOQA | GRPO | T, I | Counting , Math | trl | No | Rule-base | (2 Roadmap of Multimodal Reasoning Models / 2.3 Stage 3 Language-Centric Long Reasoning - System-2 Thinking and Planning)
• awesome-llm-and-aigc - R1-V - Agent/R1-V?style=social"/> : R1-V: Reinforcing Super Generalization Ability in Vision Language Models with Less Than $3. (Summary)
• Awesome-Multimodal-Reasoning - [🖥️Code - | GRPO | Item Counting, Number Related Reasoning and Geometry Reasoning | (Model / Image MLLM)