Ridge regression, with its preprocessing tuned, matches the deep models.

Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

[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…

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

SimMatchV2: Semi-Supervised Learning with Graph Consistency

Fast and memory-efficient exact attention

Can GPT-4 Perform Neural Architecture Search?

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

TeD-Q (Tensor-network enhanced Distributed Quantum) is a tensor network enhanced distributed hybrid quantum machine learning framework.

Official implementation for paper "LightViT: Towards Light-Weight Convolution-Free Vision Transformers"

A latent text-to-image diffusion model

[CVPR2022] Official Implementation of the paper 'Learning Where to Learn in Cross-View Self-Supervised Learning'

SimMatch: Semi-supervised Learning with Similarity Matching

Official repository for the paper "Instance-Conditioned GAN" by Arantxa Casanova, Marlene Careil, Jakob Verbeek, Michał Drożdżal, Adriana Romero-Soriano.

[ NeurIPS2021] This is an official implementation of our paper "HRFormer: High-Resolution Transformer for Dense Prediction".

Code for our paper "Regularizing Neural Networks via Adversarial Model Perturbation", CVPR2021

Code for visualizing the loss landscape of neural nets

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

[TPAMI2022 & NeurIPS2020] Official implementation of Self-Adaptive Training

RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

DomainBed is a suite to test domain generalization algorithms

Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"

OpenMMLab Self-Supervised Learning Toolbox and Benchmark

The official Pytorch implementation of OCNet, OCRNet, and SegFix.