Vidu S1: A Real-Time Interactive Video Generation Model

Multi-Block Diffusion Language Models

The official implementation of World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis

LightningRL: Breaking the Accuracy–Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning

[ICML 2026] Jacobi Forcing: Fast and Accurate Diffusion-style Decoding

[ICML 2026] d3LLM: Ultra-Fast Diffusion LLM 🚀

LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding

[CVPR 2026] Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight

Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference

Flexible and Pluggable Serving Engine for Diffusion LLMs

Doodling our way to AGI ✏️ 🖼️ 🧠

Official PyTorch implementation for "Large Language Diffusion Models"

SIFT: Grounding LLM Reasoning in Contexts via Stickers

Sky-T1: Train your own O1 preview model within $450

📖 This is a repository for organizing papers, codes and other resources related to unified multimodal models.

A unified inference and post-training framework for accelerated video generation.

Official repo for 【FaceScore: Benchmarking and Enhancing Face Quality in Human Generation】

Code for "Deep Ensemble as a Gaussian Process Posterior"

Open-Sora: Democratizing Efficient Video Production for All

Code for orthogonal neural operator

Official implementation for "LOVECon: Text-driven Training-free Long Video Editing with ControlNet"

[ICML 2024] CLLMs: Consistency Large Language Models

Implementation of soft parameter sharing for neural networks