[CVPR 2023] Official repository of paper titled "MaPLe: Multi-modal Prompt Learning".

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment (NeurIPS 2025)

This project aims to collect the latest "call for reviewers" links from various top CS/ML/AI conferences/journals

A topic-centric list of HQ open datasets.

Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"

Code for reproducing our paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"

A Python and R autograding solution

Conceptual 12M is a dataset containing (image-URL, caption) pairs collected for vision-and-language pre-training.

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

Compress conventional Vision-Language Pre-training data

The official repository of CVPR2025 paper "Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization"

Collection of awesome test-time (domain/batch/instance) adaptation methods

Official Implementation of the NeurIPS 2025 Paper "On the Value of Cross-Modal Misalignment in Multimodal Representation Learning"

Anonymous Github is a proxy server to support anonymous browsing of Github repositories for open-science code and data.

A unified source-free domain adaptation framework.

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

Pile Deduplication Code

收藏一些电子书

Evaluation tools for image captioning. Including BLEU, ROUGE-L, CIDEr, METEOR, SPICE scores.

Code to train CLIP model

A benchmarking suite for disentanglement algorithms, suited for evaluating robustness to correlated factors. Codebase for the paper "Disentanglement of Correlated Factors via Hausdorff Factorized S…