PRIS-CV / GRPO-for-LlavaLinks
GRPO Algorithm for Llava Architecture (Based on Verl)
☆44Updated 7 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☆101Updated 3 months ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆83Updated last year
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization☆99Updated last year
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)☆56Updated last year
- ☆106Updated 11 months ago
- Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"☆106Updated last week
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆84Updated last month
- MME-CoT: Benchmarking Chain-of-Thought in LMMs for Reasoning Quality, Robustness, and Efficiency☆135Updated 4 months ago
- ☆46Updated 11 months ago
- [CVPR' 25] Interleaved-Modal Chain-of-Thought☆97Updated 2 weeks ago
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆70Updated last year
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation☆125Updated 3 months ago
- [NeurIPS 2025 Spotlight] Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning☆77Updated 3 months ago
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models☆75Updated 5 months ago
- Github repository for "Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging" (ICML 2025)☆86Updated 2 months ago
- [CVPR 2024] Official Code for the Paper "Compositional Chain-of-Thought Prompting for Large Multimodal Models"☆144Updated last year
- A RLHF Infrastructure for Vision-Language Models☆187Updated last year
- (ICLR 2025 Spotlight) Official code repository for Interleaved Scene Graph.☆31Updated 4 months ago
- MMICL, a state-of-the-art VLM with the in context learning ability from ICL, PKU☆50Updated 5 months ago
- ☆28Updated 10 months ago
- A Comprehensive Survey on Evaluating Reasoning Capabilities in Multimodal Large Language Models.☆71Updated 9 months ago
- This repository is the official implementation of "Look-Back: Implicit Visual Re-focusing in MLLM Reasoning".☆73Updated 5 months ago
- VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models☆77Updated last year
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆169Updated 6 months ago
- DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding☆65Updated 6 months ago
- [ICLR 2025] VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning☆67Updated 3 months ago
- Latest open-source "Thinking with images" (O3/O4-mini) papers, covering training-free, SFT-based, and RL-enhanced methods for "fine-grain…☆104Updated 3 months ago
- [ACL 2024] Multi-modal preference alignment remedies regression of visual instruction tuning on language model☆47Updated last year
- ☆21Updated last year
- [NeurIPS 2025] MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning☆93Updated 3 months ago