Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

An extremely simple method for validation-free efficient adaptation of CLIP-like VLMs that is robust to the learning rate.

A generative world for general-purpose robotics & embodied AI learning.

Official PyTorch implementation - Video Motion Transfer with Diffusion Transformers

[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

SANE is a zero-shot inference pipeline for improving diffusion models with LLM reasoning.

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

[ECCV 2024] BrainHub: Multimodal Brain Understanding Benchmark

Openness Taxonomy of Large Language Models

【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

This is the official repo of the paper "Latent Guard: a Safety Framework for Text-to-image Generation"

[ICLR 2025] HQ-Edit: A High-Quality and High-Coverage Dataset for General Image Editing

[ECCV 2024] UMBRAE: Unified Multimodal Brain Decoding | Unveiling the 'Dark Side' of Brain Modality

This repo lists relevant papers summarized in our survey paper: A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models.

[CVPR 2024 Oral, Best Paper Award Candidate] Official repository of "PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness"

Open-Sora: Democratizing Efficient Video Production for All

Original code base for On Pretraining Data Diversity for Self-Supervised Learning

DeepLens: A differentiable lens simulator for end-to-end computational cameras.

Official Code for Stable Cascade

Code base of SynthCLIP: CLIP training with purely synthetic text-image pairs from LLMs and TTIs.

InstructPix2Pix with distilled diffusion models

Learning from synthetic data - code and models

Scene-Conditional 3D Object Stylization and Composition (ECCV 2024)

collection of diffusion model papers categorized by their subareas

[CVPR 2024] Official repository of "A Simple Recipe for Language-guided Domain Generalized Segmentation"

[CVPR 2024] Official repository of "Material Palette: Extraction of Materials from a Single Real-world Image"