PRIS-CV / GRPO-for-LlavaLinks
GRPO Algorithm for Llava Architecture (Based on Verl)
☆47Updated 8 months ago
Alternatives and similar repositories for GRPO-for-Llava
Users that are interested in GRPO-for-Llava are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2025] NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆104Updated 4 months ago
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization☆100Updated 2 years ago
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)☆58Updated last year
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆84Updated 3 months ago
- Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"☆110Updated last month
- MME-CoT: Benchmarking Chain-of-Thought in LMMs for Reasoning Quality, Robustness, and Efficiency☆137Updated 5 months ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆85Updated last year
- ☆110Updated last year
- ☆28Updated 11 months ago
- DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding☆66Updated 7 months ago
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models☆77Updated 6 months ago
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆69Updated last year
- [ACL 2024] Multi-modal preference alignment remedies regression of visual instruction tuning on language model☆48Updated last year
- [NeurIPS 2025 Spotlight] Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning☆78Updated 4 months ago
- ☆46Updated last year
- (ICLR 2025 Spotlight) Official code repository for Interleaved Scene Graph.☆31Updated 5 months ago
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆179Updated 7 months ago
- [CVPR 2024] Official Code for the Paper "Compositional Chain-of-Thought Prompting for Large Multimodal Models"☆145Updated last year
- A RLHF Infrastructure for Vision-Language Models☆193Updated last year
- Github repository for "Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging" (ICML 2025)☆88Updated 4 months ago
- [CVPR' 25] Interleaved-Modal Chain-of-Thought☆106Updated last month
- [ICML 2025] Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in…☆185Updated 4 months ago
- VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models☆77Updated last year
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation☆132Updated 4 months ago
- Official implement of MIA-DPO☆70Updated last year
- MMICL, a state-of-the-art VLM with the in context learning ability from ICL, PKU☆50Updated 6 months ago
- This repository is the official implementation of "Look-Back: Implicit Visual Re-focusing in MLLM Reasoning".☆83Updated 6 months ago
- [ICLR'26] Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology☆72Updated this week
- Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency☆60Updated 7 months ago
- [CVPR 2025 (Oral)] Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key☆102Updated 3 weeks ago