Skip To Main Content
Win Kent on Muck Rack

Win Kent

As seen in: arXiv
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile
Back to Win Kent’s profile

Articles by Win Kent

Computer Science > Machine Learning

|
By Win Kent, Chee Seng, Teresa Pui Yee
| arXiv
Machine unlearning (MU) is commonly judged by output forgetting, such as low forget-set accuracy or reduced logit-level membership inference. But if output-level success can coexist with retraining-inconsistent residuals in representation space, what kind of forgetting are current evaluations actually certifying?
Open in Who Shared Issue with article?

[2502.12176] Ten Challenging Problems in Federated Foundation Models

|
By Chee Seng, Win Kent
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (402) Issue with article?

IPR-NeRF: Ownership Verification meets Neural Radiance Field

|
By Kam Woh, Chee Seng, Win Kent, Yi Zhe
| arXiv
arXiv:2401.09495 (cs) This paper has been withdrawn by WinKent Ong [Submitted on 17 Jan 2024 (v1), last revised 23 Jan 2024 (this version, v4)] No PDF available, click to view other formats Comments: Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2401.09495 [cs.CV] (or arXiv:2401.09495v4 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2401.09495 Submission history From: WinKent Ong [ view email] [v1] Wed, 17 Jan 2024 01:33:40 UTC (24,300 KB) [v2] Fri, 19 Jan...
Open in Who Shared View Duplicates (696) Issue with article?
Show More