official implementation of "Interpreting CLIP's Image Representation via Text-Based Decomposition"

[CVPR 2024] Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

Official implementation of "Describing Differences in Image Sets with Natural Language" (CVPR 2024 Oral)

Code and datasets for "What’s “up” with vision-language models? Investigating their struggle with spatial reasoning".

📄 A curated list of visual reasoning papers.

[CVPR 2024] OneLLM: One Framework to Align All Modalities with Language

[CVPR 2024 Highlight] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

mPLUG-Owl: The Powerful Multi-modal Large Language Model Family

Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey

[CVPR'24] Validation-free few-shot adaptation of CLIP, using a well-initialized Linear Probe (ZSLP) and class-adaptive constraints (CLAP).

[ACL2023, Findings] Source codes for the paper "Werewolf Among Us: Multimodal Resources for Modeling Persuasion Behaviors in Social Deduction Games"

NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024

[CVPR24 Highlights] Polos: Multimodal Metric Learning from Human Feedback for Image Captioning

Official repository for the MMFM challenge

[CVPR 2024] MAPLM: A Large-Scale Vision-Language Dataset for Map and Traffic Scene Understanding

Official Implementation for "MyVLM: Personalizing VLMs for User-Specific Queries" (ECCV 2024)

[AAAI-25] Cobra: Extending Mamba to Multi-modal Large Language Model for Efficient Inference

This is the official repository for the LENS (Large Language Models Enhanced to See) system.

(CVPR2024)A benchmark for evaluating Multimodal LLMs using multiple-choice questions.

CLIP+MLP Aesthetic Score Predictor

Refine high-quality datasets and visual AI models

[ECCV 2024] InstructIR: High-Quality Image Restoration Following Human Instructions https://huggingface.co/spaces/marcosv/InstructIR

【TMM 2025🔥】 Mixture-of-Experts for Large Vision-Language Models

【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

[CVPR2024] The code for "Osprey: Pixel Understanding with Visual Instruction Tuning"