One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Specification and documentation for Agent Skills

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

PyTorch implementation of machine unlearning [torchunlearn] @ NeurIPS 2025 "Unlearning-Aware Minimization"

[NeurIPS25] Official repo for "Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning"

[NeurIPS 2025] DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers

[NeurIPS D&B '25] The one-stop repository for LLM unlearning

Tools for merging pretrained large language models.

Official inference repo for FLUX.1 models

[NeurIPS24] "What makes unlearning hard and what to do about it" [NeurIPS24] "Scalability of memorization-based machine unlearning"

LLM Council works together to answer your hardest questions

[COLM2025]"LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks"

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

SAM 3D Objects

[ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)

[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat

Official implementation of "Continuous Autoregressive Language Models"

Sparsity Outperforms Low-Rank Projections in Few-Shot Adaptation

RICO-Benchmark

[ICCV 2025] Official implementation of the paper: "Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-time Open-Vocabulary Object Detection"

Anthropic's Interactive Prompt Engineering Tutorial

Official Implementation of "OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation" (NeurIPS 2025).

A generative AI extension for JupyterLab

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

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

[arXiv] Mitigating Cross-Image Information Leakage in LVLMs for Multi-Image Tasks