An official implementation of Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching

CastleHill: Separable Causal Diffusion / Varitaion Flow Maps for LTX-2 long-form video generation

CVPR 2026 (Highlight)-Guiding a Diffusion Transformer with the Internal Dynamics of Itself (IG)

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

🧂 Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation

MOVA: Towards Scalable and Synchronized Video–Audio Generation

NVIDIA FastGen: Fast Generation from Diffusion Models

Gen-Searcher: Reinforcing Agentic Search for Image Generation

ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation

Codebase for PrismMirror: Real-Time Human Frontal View Synthesis from a Single Image

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Code and website for Self-Flow: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis

Implementation of "Too Vivid to Be Real? Benchmarking and Calibrating Generative Color Fidelity".

Predicting the generation FID of latent diffusion, with a variant of reconstruction FID of Variational Auto-encoder.

Official code for paper Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models

[ICLR 2026] Self-Representation Alignment for Diffusion Transformers (SRA)

[NeurIPS 2025] VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models

Helios: Real Real-Time Long Video Generation Model

Official Codebase for "DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos"

Reinforcement Learning Framework for Visual Generation

Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation"

Elevate your AI research writing, no more tedious polishing ✨

[CVPR 2026] VDOT: Efficient Unified Video Creation via Optimal Transport Distillation

Towards Scalable Pre-training of Visual Tokenizers for Generation

[ICLR 2026] This is the official PyTorch implementation of "QVGen: Pushing the Limit of Quantized Video Generative Models".

[ICLR 2026] LongLive: Real-time Interactive Long Video Generation

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage