2026/07/03
Research
Introducing Vidu S1: Real-Time Interactive Video Generation
Read Paper
2026/04/29
Research
Motubrain: An Advanced World Action Model for Robot Control
Read Paper
2025/12/15
Research
Motus: A Unified Latent Action World Model
Read Paper
2025/12/10
Open Source
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Read Paper
2025/09/28
Research
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
Read Paper
2025/07/17
Research
Vidar: Embodied Video Diffusion Model for Generalist Manipulation
Read Paper
2024/10/03
Research
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration
Read Paper
2024/05/07
Research
Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models
Read Paper
2023/03/12
Research
One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale
Read Paper
2022/09/25
Research
All are Worth Words: A ViT Backbone for Diffusion Models
Read Paper
2022/01/17
Research
Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models
Read Paper
