Enhancing Motion Dynamics of Image-to-Video Models via Adaptive Low-Pass Guidance (arXiv 2025)

verl: Volcano Engine Reinforcement Learning for LLMs

Kimi K2 is the large language model series developed by Moonshot AI team

Long-RL: Scaling RL to Long Sequences

Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion by finetuning them using various r…

[ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

This checklist is designed to help you systematically prepare and polish academic papers for top conferences and journals (e.g., ICML, NeurIPS, CVPR). It incorporates widely recommended best practi…

JAX implementation of MeanFlow

🚀 Efficient implementations of state-of-the-art linear attention models

plotting on terminal

Official repository for the paper "TIIF-Bench: How Does Your T2I Model Follow Your Instructions?".

[ICCV'25] Manual-PA: Learning 3D Part Assembly from Instruction Diagrams

Official Implementation of Diffusion Step Annealing (DiSA) in Autoregressive Image Generation

Open-source unified multimodal model

WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation

OpenMTP - Advanced Android File Transfer Application for macOS

Interactive visualizations of the geometric intuition behind diffusion models.

Official implementation of UnifiedReward & UnifiedReward-Think

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

Official repository of T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

MAGI-1: Autoregressive Video Generation at Scale

Official Implementation for paper: Negative Token Merging: Image-based Adversarial Feature Guidance

Official code for Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing

Code for our paper: Learning Camera Movement Control from Real-World Drone Videos

Lets make video diffusion practical!