9 papers · 1 filter
DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency
Zeqi Xiao, Qingle Liu, Kaiwen Zhang +3
Autoregressive video diffusion supports streaming generation and interactive control, but its KV cache grows continuously with the generated history. Existing compression strategie…
Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation
Zeqi Xiao, Yiwei Zhao, Lingxiao Li +6
We investigate whether video generative models can exhibit visuospatial intelligence, a capability central to human cognition, using only visual data. To this end, we present Video…
Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers
Yifan Zhou, Zeqi Xiao, Tianyi Wei +2
Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to long token sequences. Recent To…
Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention
Taiye Chen, Zihan Ding, Anjian Li +4
Recent advancements in video generation has shifted from bidirectional models for short videos to autoregressive ones for ultra long video generation. Previous models, which usuall…
Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors
Songlin Yang, Tianyi Wei, Yushi Lan +3
Semantic matching aims to establish pixel-level correspondences between instances of the same category and represents a fundamental task in computer vision. Existing approaches suf…
WorldMem: Long-term Consistent World Simulation with Memory
Zeqi Xiao, Yushi Lan, Yifan Zhou +4
World simulation has gained increasing popularity due to its ability to model virtual environments and predict the consequences of actions. However, the limited temporal context wi…
Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space
Yifan Zhou, Zeqi Xiao, Shuai Yang +1
Latent Diffusion Models (LDMs) are known to have an unstable generation process, where even small perturbations or shifts in the input noise can lead to significantly different out…
Trajectory Attention for Fine-grained Video Motion Control
Zeqi Xiao, Wenqi Ouyang, Yifan Zhou +4
Recent advancements in video generation have been greatly driven by video diffusion models, with camera motion control emerging as a crucial challenge in creating view-customized v…
Video Diffusion Models are Training-free Motion Interpreter and Controller
Zeqi Xiao, Yifan Zhou, Shuai Yang +1
Video generation primarily aims to model authentic and customized motion across frames, making understanding and controlling the motion a crucial topic. Most diffusion-based studie…