UCSC-VLAA / VLAA-ThinkingLinks
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
☆135Updated 5 months ago
Alternatives and similar repositories for VLAA-Thinking
Users that are interested in VLAA-Thinking are comparing it to the libraries listed below
Sorting:
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆109Updated 4 months ago
- [NeurIPS 2025] NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆91Updated 2 weeks ago
- ☆91Updated 8 months ago
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆151Updated 4 months ago
- Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"☆85Updated last month
- A RLHF Infrastructure for Vision-Language Models☆184Updated 10 months ago
- A Self-Training Framework for Vision-Language Reasoning☆86Updated 8 months ago
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization☆93Updated last year
- Offical Repository of "AtomThink: Multimodal Slow Thinking with Atomic Step Reasoning"☆56Updated 2 months ago
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆70Updated last year
- MME-CoT: Benchmarking Chain-of-Thought in LMMs for Reasoning Quality, Robustness, and Efficiency☆130Updated 2 months ago
- Github repository for "Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging" (ICML 2025)☆74Updated last week