zhyang2226 / OPA-DPOLinks
[CVPR 2025 (Oral)] Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
☆71Updated 2 months ago
Alternatives and similar repositories for OPA-DPO
Users that are interested in OPA-DPO are comparing it to the libraries listed below
Sorting:
- 🔥CVPR 2025 Multimodal Large Language Models Paper List☆152Updated 5 months ago
- [ECCV 2024] API: Attention Prompting on Image for Large Vision-Language Models☆102Updated 10 months ago
- [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'☆190Updated last month
- [Neurips'24 Spotlight] Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought …☆368Updated 8 months ago
- VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models☆72Updated last year
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models☆67Updated last month
- Latest open-source "Thinking with images" (O3/O4-mini) papers, covering training-free, SFT-based, and RL-enhanced methods for "fine-grain…☆87Updated last week
- Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning☆62Updated 3 months ago
- ☆136Updated 6 months ago
- [ICLR'25] Official code for the paper 'MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs'☆249Updated 4 months ago
- [CVPR' 25] Interleaved-Modal Chain-of-Thought☆80Updated last week
- [ECCV 2024] Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs☆135Updated 9 months ago
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization☆91Updated last year
- Collections of Papers and Projects for Multimodal Reasoning.☆105Updated 4 months ago
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation☆99Updated 8 months ago
- MME-CoT: Benchmarking Chain-of-Thought in LMMs for Reasoning Quality, Robustness, and Efficiency☆125Updated 3 weeks ago
- [CVPR 2025 Oral] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection☆111Updated last month
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆120Updated 5 months ago
- [ICML 2025] Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in…☆145Updated last month
- [ICLR'25] Reconstructive Visual Instruction Tuning☆105Updated 4 months ago
- Survey: https://arxiv.org/pdf/2507.20198☆121Updated last week
- [NeurIPS 2024] Visual Perception by Large Language Model’s Weights☆45Updated 5 months ago
- ☆105Updated 5 months ago
- [Blog 1] Recording a bug of grpo_trainer in some R1 projects☆20Updated 6 months ago
- This repository is the official implementation of "Look-Back: Implicit Visual Re-focusing in MLLM Reasoning".☆47Updated last month
- ☆67Updated last month
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆142Updated 2 months ago
- Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency☆49Updated 2 months ago
- R1-like Video-LLM for Temporal Grounding☆114Updated 2 months ago
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆97Updated last week