Hierarchical Text Classification Optimization via Structural Entropy and Singular Smoothing

Official Implementation for the ICML2022 paper "Directed Acyclic Transformer for Non-Autoregressive Machine Translation"

A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.

[CVPR 2024 Highlight] Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer

Nymeria: a massive collection of multimodal egocentric daily motion in the wild

Fine-Grained Open Domain Image Animation with Motion Guidance

COLMAP - Structure-from-Motion and Multi-View Stereo

Official implementation of AnimateDiff.

Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"

The official repository of "Spectral Motion Alignment for Video Motion Transfer using Diffusion Models".

This is the official implementation of FADE: Frequency-Aware Diffusion Model Factorization for Video Editing (CVPR 2025)

CVPR2025:AnimateAnything

Source code of paper "Frequency-based Motion Representation for Video Generative Adversarial Networks", TIP 2023

Official source code of "MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion", published in ICLR 2025

Official Pytorch Implementation of Our CVPR2023 Paper: "Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization"

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?

Erasing Concepts from Diffusion Models

CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control

[ ECCV 2024 ] MotionLCM: This repo is the official implementation of "MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model"

MotionGPT3: Human Motion as a Second Modality, a MoT-based framework for unified motion understanding and generation

[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs

Official code implementation of SKU, Accepted by ACL 2024 Findings

[ECCV 2022] Compositional Generation using Diffusion Models

a simple unofficial implementation of classifier-free diffusion guidance

Implementation of "S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models"