K
Kaiwen Xue
Researcher at Beijing Normal University
Publications - 5
Citations - 25
Kaiwen Xue is an academic researcher from Beijing Normal University. The author has contributed to research in topics: Computer science & Cache. The author has an hindex of 1, co-authored 1 publications receiving 4 citations.
Papers
More filters
Journal ArticleDOI
One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale
Fan Bao,Shen Nie,Kaiwen Xue,Chongxuan Li,Shiliang Pu,Yaole Wang,Gang Yue,Yue Cao,Hang Su,Jun Zhu +9 more
TL;DR: UniDiffuser as mentioned in this paper proposes a unified diffusion framework (dubbed UniDiffuser) to fit all distributions relevant to a set of multi-modal data in one model.
All are Worth Words: A ViT Backbone for Diffusion Models
TL;DR: Zhang et al. as mentioned in this paper designed a simple and general ViT-based architecture (named U-ViT) for image generation with diffusion models, which is characterized by treating all inputs including the time, condition and noisy image patches as tokens and employing long skip connections between shallow and deep layers.
Book ChapterDOI
Analyzing Customer’s Product Preference Using Wireless Signals
TL;DR: The key insight of PreFi is to extract the variance features of the fine-grained time-series CSI, which is sensitively affected by customer activity, to recognize what is the customer doing.
Journal ArticleDOI
Efficient real-time video conferencing with adaptive frame delivery
TL;DR: Tyrus as mentioned in this paper is a real-time video conferencing system that enables adaptive delivery of B-frames, prioritizing the allocation of bandwidth to other crucial video frames.
Proceedings ArticleDOI
Contiguitas: The Pursuit of Physical Memory Contiguity in Datacenters
Kai Yang Zhao,Kaiwen Xue,Ziqi Wang,Dan Schatzberg,Leon Yang,Antonis Manousis,Johannes Weiner,Bikash Sharma,Chunqiang Tang,Dimitrios Skarlatos +9 more
TL;DR: Contiguitas as mentioned in this paper proposes to separate regular movable allocations from unmovable ones by placing them into two different continuous regions in physical memory and dynamically adjusting the boundary of the two regions based on memory demand.