Fast and memory-efficient exact attention

Heterogeneous Pre-trained Transformer (HPT) as Scalable Policy Learner.

ViViD: Video Virtual Try-on using Diffusion Models

[AAAI 2025] Official implementation of "TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment"

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

[ECCV24] VISA: Reasoning Video Object Segmentation via Large Language Model

[Arxiv 2024] From Parts to Whole: A Unified Reference Framework for Controllable Human Image Generation

[NeurlPS 2024] One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

Official implementation of OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

Let your Claude able to think

Inpaint anything using Segment Anything and inpainting models.

KITS: Inductive Spatio-Temporal Kriging with Increment Training Strategy (AAAI'25)

Official implementation of the paper "Spatial-Temporal Large Language Model for Traffic Prediction"

Hybrid Mamba for Few-Shot Segmentation (NIPS 2024)

Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

[CVPR2024] StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Eliminating Feature Ambiguity for Few-Shot Segmentation (ECCV'24)

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

PyTorch native post-training library

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

Development repository for the Triton language and compiler

This is the official implementation for our NeurIPS 2023 paper "Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation".

Build high-performance AI models with modular building blocks

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