Stop hook for Claude Code that keeps the agent working until all plans and user requests are 100% complete

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

Processed / Cleaned Data for Paper Copilot

Simple RL training for reasoning

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Modeling, training, eval, and inference code for OLMo

[ICCV 2025] The official code of the paper "Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate".

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

A framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings.

Easily compute clip embeddings and build a clip retrieval system with them

What do we learn from inverting CLIP models?

Self-Supervised Dataset Distillation for Transfer Learning

Open-Sora: Democratizing Efficient Video Production for All

A curated, but incomplete, list of data-centric AI resources.

Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"

DataComp: In search of the next generation of multimodal datasets

This is the repository for the Photorealistic Unreal Graphics (PUG) datasets for representation learning.

SpuCo is a Python package developed to further research to address spurious correlations.

A library for efficient similarity search and clustering of dense vectors.

A beautiful, simple, clean, and responsive Jekyll theme for academics

A synthetic image augmentation library for object detection tasks.

Source code for ClimateLearn

Official Code for ICML 2023 Data-Efficient Contrastive Self-supervised Learning

[ NeurIPS 2022 ] Official Codebase for "ETAB: A Benchmark Suite for Visual Representation Learning in Echocardiography"

🐍 Geometric Computer Vision Library for Spatial AI

Dataset Condensation (ICLR21 and ICML21)

Pretrained models on CIFAR10/100 in PyTorch