PRIS-CV / GRPO-for-LlavaLinks
GRPO Algorithm for Llava Architecture (Based on Verl)
☆37Updated 4 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:
- NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆88Updated last month
- MME-CoT: Benchmarking Chain-of-Thought in LMMs for Reasoning Quality, Robustness, and Efficiency☆128Updated last month
- [CVPR' 25] Interleaved-Modal Chain-of-Thought☆85Updated last month
- Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning☆63Updated 4 months ago
- SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models☆132Updated 4 months ago
- This repository is the official implementation of "Look-Back: Implicit Visual Re-focusing in MLLM Reasoning".☆55Updated 2 months ago
- A Comprehensive Survey on Evaluating Reasoning Capabilities in Multimodal Large Language Models.☆68Updated 6 months ago
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆80Updated last year
- Interleaving Reasoning: Next-Generation Reasoning Systems for AGI☆155Updated last week
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization☆91Updated last year
- A RLHF Infrastructure for Vision-Language Models☆183Updated 10 months ago
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆70Updated last year
- (ICLR 2025 Spotlight) Official code repository for Interleaved Scene Graph.☆28Updated last month
- A Self-Training Framework for Vision-Language Reasoning☆84Updated 7 months ago
- Official implement of MIA-DPO☆65Updated 7 months ago
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆144Updated 3 months ago
- VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models☆73Updated last year
- This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vi…☆114Updated 3 months ago
- Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"☆85Updated 3 weeks ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆81Updated 10 months ago
- An Arena-style Automated Evaluation Benchmark for Detailed Captioning☆55Updated 3 months ago
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models☆69Updated 2 months ago
- ☆45Updated 8 months ago
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)☆55Updated 10 months ago
- Doodling our way to AGI ✏️ 🖼️ 🧠☆102Updated 3 months ago
- ☆69Updated this week
- Github repository for "Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging" (ICML 2025)☆74Updated 3 months ago
- ☆43Updated 2 months ago
- MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision☆25Updated 3 months ago
- ☆46Updated 5 months ago