K
Kai Li
Researcher at Princeton University
Publications - 328
Citations - 76948
Kai Li is an academic researcher from Princeton University. The author has contributed to research in topics: Computer science & Cache. The author has an hindex of 76, co-authored 220 publications receiving 56127 citations. Previous affiliations of Kai Li include EMC Corporation & Baylor College of Medicine.
Papers
More filters
Proceedings Article
Evaluating Gradient Inversion Attacks and Defenses in Federated Learning
TL;DR: In this paper, the authors evaluate the benefits of three proposed defense mechanisms against gradient inversion attacks and show the trade-offs of privacy leakage and data utility of these defense methods, and find that combining them in an appropriate manner makes the attack less effective.
Proceedings ArticleDOI
Retrospective: virtual memory mapped network interface for the SHRIMP multicomputer
Matthias A. Blumrich,Kai Li,Richard D. Alpert,Cezary Dubnicki,Edward W. Felten,Jonathan Sandberg +5 more
Journal ArticleDOI
SSDNeRF: Semantic Soft Decomposition of Neural Radiance Fields
Siddhant Ranade,Christoph Lassner,Kai Li,Christian Haene,Shen Chi-Chen,Jean-Charles Bazin,Sofien Bouaziz +6 more
TL;DR: In this article , the authors proposed a semantic soft decomposition of neural radiance fields (SSDNeRF) which jointly encodes semantic signals in combination with radiance signals of a scene.
Proceedings ArticleDOI
Fast Few-shot Debugging for NLU Test Suites
TL;DR: This work studies few-shot debugging of transformer based natural language understanding models, using recently popularized test suites to not just diagnose but correct a problem.
Proceedings Article
Patient-Specific Effects of Medication Using Latent Force Models with Gaussian Processes.
Li-Fang Cheng,Bianca Dumitrascu,Michael Minyi Zhang,Corey Chivers,Michael Draugelis,Kai Li,Barbara E. Engelhardt +6 more
TL;DR: In this paper, the effect of interventions is modeled as a hybrid Gaussian process composed of a GP capturing patient physiology convolved with a latent force model capturing effects of treatments on specific physiological features.