PRIS-CV / GRPO-for-LlavaLinks
GRPO Algorithm for Llava Architecture (Based on Verl)
☆22Updated last month
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 2024] Calibrated Self-Rewarding Vision Language Models☆76Updated last year
- [ICCV 2025] VisRL: Intention-Driven Visual Perception via Reinforced Reasoning☆30Updated 2 weeks ago
- NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆72Updated 3 weeks ago
- [CVPR' 25] Interleaved-Modal Chain-of-Thought☆53Updated 2 months ago
- Official implement of MIA-DPO☆58Updated 5 months ago
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization☆88Updated last year
- A Comprehensive Survey on Evaluating Reasoning Capabilities in Multimodal Large Language Models.☆64Updated 3 months ago
- MMICL, a state-of-the-art VLM with the in context learning ability from ICL, PKU☆48Updated last year
- Official implementation of "Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation" (CVPR 202…☆30Updated last month
- DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding☆63Updated 2 weeks ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆75Updated 7 months ago
- ☆26Updated 7 months ago
- A Self-Training Framework for Vision-Language Reasoning☆80Updated 5 months ago
- ☆24Updated 4 months ago
- ☆80Updated 5 months ago
- [ACL 2024] Multi-modal preference alignment remedies regression of visual instruction tuning on language model☆46Updated 7 months ago
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)☆51Updated 8 months ago
- [ACL 2024] Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models. Detect and mitigate object hallucinatio…☆22Updated 5 months ago
- ACL'24 (Oral) Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback☆65Updated 9 months ago
- Emerging Pixel Grounding in Large Multimodal Models Without Grounding Supervision☆41Updated 3 months ago
- [LLaVA-Video-R1]✨First Adaptation of R1 to LLaVA-Video (2025-03-18)☆29Updated last month
- TimeChat-online: 80% Visual Tokens are Naturally Redundant in Streaming Videos☆51Updated last week
- HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data (Accepted by CVPR 2024)☆45Updated 11 months ago
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models☆38Updated 11 months ago
- Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency☆43Updated 3 weeks ago
- ☆87Updated 3 months ago
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆68Updated last year
- ☆44Updated 6 months ago
- Preference Learning for LLaVA☆46Updated 7 months ago
- [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'☆181Updated last month