Distill Minimax-H3 into 4 steps

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

MAGI-2-preview: Scaling Video Generation Models Efficiently

[ICML2026] Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization

Official repo for paper "Echo-Infinity: Learnable Evolving Memory for Real-Time Infinite Video Generation"

Official code for Echo-Memory: a controlled study of memory in action-conditioned video world models (Context, Compression, Spatial, State-Space).

Code for the paper HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement

[SIGGRAPH Asia 26 Conditionally Accept]PAct: Part-Decomposed Single-View Articulated Object Generation

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Infinite Worlds with Versatile Interactions

[ECCV 2026] WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG

Code for MIRA: Multiplayer Interactive World Models with Representation Autoencoders

EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis

DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation

AI PPT赛道终结者，史上最最最强 PPT Skill！！！ 使用GPT生成豪华的图片格式PPT，然后转换为完全可编辑的PPTX文件。

Wan: Open and Advanced Large-Scale Video Generative Models

A toolkit for speaker diarization.

Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.

JoyAI-Echo: Pushing the Frontier of Long Audio-Visual Generation

Official page of ImmerIris: A Large-Scale Dataset and Benchmark for Off-Axis and Unconstrained Iris Recognition in Immersive Applications.

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models