CX
Chendong Xiang
cs.CVcs.LGcs.AIcs.ROcs.ARcs.PF
On Valency
published · living versionsW_5y4khhex·v1 · currentpublished
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
with Jintao Zhang, Kai Jiang, Jintao Chen, Xu Wang +30
1 version
Preprints & journals
14 papers in the corpus · 2023–2026Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation2609.11638v1 · Jintao Zhang, Kai Jiang, Jintao Chen et al.2026 · 0 citationsarXivon Valency
Vidu S1: A Real-Time Interactive Video Generation Model2607.03118v2 · Jintao Zhang, Kai Jiang, Jintao Chen et al.2026 · 0 citationsarXiv
Motubrain: An Advanced World Action Model for Robot Control2604.27792v5 · Motubrain Team, Chendong Xiang, Fan Bao et al.2026 · 0 citationsarXiv
SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning2602.13515v2 · Jintao Zhang, Kai Jiang, Chendong Xiang et al.2026 · 0 citationsarXiv
Geometry-Aware Rotary Position Embedding for Consistent Video World Model2602.07854v3 · Chendong Xiang, Jiajun Liu, Jintao Zhang et al.2026 · 0 citationsarXiv
Vidarc: Embodied Video Diffusion Model for Closed-loop Control2512.17661v1 · Yao Feng, Chendong Xiang, Xinyi Mao et al.2025 · 0 citationsarXiv
Motus: A Unified Latent Action World Model2512.13030v2 · Hongzhe Bi, Hengkai Tan, Shenghao Xie et al.2025 · 0 citationsarXiv
Vidar: Embodied Video Diffusion Model for Generalist Manipulation2507.12898v4 · Yao Feng, Hengkai Tan, Xinyi Mao et al.2025 · 0 citationsarXiv
SageAttention2++: A More Efficient Implementation of SageAttention22505.21136v3 · Jintao Zhang, Xiaoming Xu, Jia Wei et al.2025 · 0 citationsarXiv
SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference2502.18137v8 · Jintao Zhang, Chendong Xiang, Haofeng Huang et al.2025 · 0 citationsProceedings of the 42 nd International Conference on Machine Learning, PMLR 267, 2025 (ICML 2025)
Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model2406.15735v3 · Min Zhao, Hongzhou Zhu, Chendong Xiang et al.2024 · 4 citationsarXiv
Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models2405.04233v1 · Fan Bao, Chendong Xiang, Gang Yue et al.2024 · 1 citationarXiv
CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model2403.05034v1 · Zhengyi Wang, Yikai Wang, Yifei Chen et al.2024 · 91 citationsarXiv
A Closer Look at Parameter-Efficient Tuning in Diffusion Models2303.18181v2 · Chendong Xiang, Fan Bao, Chongxuan Li et al.2023 · 3 citationsarXiv
Career total: 14 works. 14 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.