findalexli / mllm-dpoLinks
[ACL 2024] Multi-modal preference alignment remedies regression of visual instruction tuning on language model
☆46Updated 6 months ago
Alternatives and similar repositories for mllm-dpo
Users that are interested in mllm-dpo are comparing it to the libraries listed below
Sorting:
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)☆50Updated 7 months ago
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization☆88Updated last year
- This is the official repo for Debiasing Large Visual Language Models, including a Post-Hoc debias method and Visual Debias Decoding strat…☆78Updated 3 months ago
- ☆77Updated 4 months ago
- The codebase for our EMNLP24 paper: Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Mo…☆78Updated 4 months ago
- ☆91Updated last year
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆74Updated 11 months ago
- [NeurIPS'24] Official PyTorch Implementation of Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment☆56Updated 8 months ago
- ☆37Updated 10 months ago
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆67Updated last year
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆74Updated 6 months ago
- ☆43Updated 5 months ago
- Official implement of MIA-DPO☆58Updated 4 months ago
- code for "Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization"☆55Updated 9 months ago
- Preference Learning for LLaVA☆45Updated 6 months ago
- ☆99Updated last year
- SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models☆112Updated last month
- VideoNIAH: A Flexible Synthetic Method for Benchmarking Video MLLMs☆47Updated 2 months ago
- HallE-Control: Controlling Object Hallucination in LMMs☆31Updated last year
- [SCIS 2024] The official implementation of the paper "MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Di…☆52Updated 6 months ago
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding☆47Updated 5 months ago
- VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models☆63Updated 10 months ago
- ☆63Updated last year
- HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data (Accepted by CVPR 2024)☆45Updated 10 months ago
- VideoHallucer, The first comprehensive benchmark for hallucination detection in large video-language models (LVLMs)☆30Updated 2 months ago
- DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding☆56Updated 2 months ago
- ☆74Updated 11 months ago
- Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning☆22Updated 8 months ago
- ACL'24 (Oral) Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback☆65Updated 8 months ago
- [Arxiv] Aligning Modalities in Vision Large Language Models via Preference Fine-tuning☆86Updated last year