10 papers · 1 filter
PhysFlow: Physics-Aware Optical Flow for Motion Controllable Video Generation
Cong Wang, Hanxin Zhu, Yonglin Tian +5
Video generation models have recently attracted substantial attention for their ability to generate visually compelling videos, yet ensuring physically consistent and plausible dyn…
Token Radius Attention for Efficient Video Generation
Jiayu Chen, Zhikun Jiang, Maoliang Li +6
Video Diffusion Transformers (VDiTs) enable high-fidelity generation but incur quadratic cost from dense 3D self-attention. Existing head- and block-level sparse methods share comp…
Embody4D: A Generalist Data Engine for Embodied 4D World Modeling
Peiyan Tu, Hanxin Zhu, Jingwen Sun +6
Embodied agents require robust and comprehensive 3D spatiotemporal representations to support spatial reasoning, manipulation understanding, and downstream decision making. However…
Physics-Informed Video Generation via Mixture-of-Experts Latent Alignment
Cong Wang, Hanxin Zhu, Jiayi Luo +6
Large-scale video generation models have made remarkable progress in semantic consistency and visual quality, producing videos that are increasingly coherent and visually convincin…
Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation
Jiayi Luo, Qiyan Liu, Tengyang Wang +8
Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens.…
EntroAD: Structural Entropy-Guided Prompt Adaptation for Zero-Shot Anomaly Detection
Xinyu Zhao, Qingyun Sun, Jiayi Luo +1
Zero-Shot Anomaly Detection (ZSAD) aims to detect anomalies in unseen domains without target-domain adaptation. Recent CLIP-based methods have shown promising performance by levera…
Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation
Jiayu Chen, Junbei Tang, Wenbiao Zhao +6
Autoregressive video generation enables streaming and open-ended long video synthesis, but still suffers from long-term degradation caused by accumulated errors. Existing KVCache s…
GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusion
Hanxin Zhu, Cong Wang, Peiyan Tu +4
Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of domains including spatial intellige…
OrthoPhys: Physically Plausible Video Generation with Orthogonal-View Geometry Guidance
Cong Wang, Hanxin Zhu, Xiao Tang +4
Recent progress in video generation has led to substantial improvements in visual fidelity, yet ensuring physically consistent motion remains a fundamental challenge. Intuitively,…
Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering
Jiayi Luo, Jiayu Chen, Jiankun Wang +6
Diffusion Transformers (DiTs) achieve strong video generation quality but suffer from high inference cost due to dense 3D attention, motivating sparse attention techniques for impr…