Zobrazeno 1 - 10
of 2 149
pro vyhledávání: '"Wu Zhiwei"'
Information disclosure can compromise privacy when revealed information is correlated with private information. We consider the notion of inferential privacy, which measures privacy leakage by bounding the inferential power a Bayesian adversary can g
Externí odkaz:
http://arxiv.org/abs/2410.17095
Autor:
Thaker, Pratiksha, Hu, Shengyuan, Kale, Neil, Maurya, Yash, Wu, Zhiwei Steven, Smith, Virginia
Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning research community has increasingly turned toward empirical benchmarks t
Externí odkaz:
http://arxiv.org/abs/2410.02879
Autor:
Wu, Zhiwei, Zhang, Jinhui
Magnetic soft continuum robots (MSCRs) have emerged as powerful devices in endovascular interventions owing to their hyperelastic fibre matrix and enhanced magnetic manipulability. Effective closed-loop control of tethered magnetic devices contribute
Externí odkaz:
http://arxiv.org/abs/2408.03017
Autor:
Liu, Terrance, Wu, Zhiwei Steven
While large language models are rapidly moving towards consumer-facing applications, they are often still prone to factual errors and hallucinations. In order to reduce the potential harms that may come from these errors, it is important for users to
Externí odkaz:
http://arxiv.org/abs/2407.21057
As the U.S. Census Bureau implements its controversial new disclosure avoidance system, researchers and policymakers debate the necessity of new privacy protections for public statistics. With experiments on both published statistics and synthetic da
Externí odkaz:
http://arxiv.org/abs/2407.04776
Publikováno v:
BIO Web of Conferences, Vol 59, p 01019 (2023)
Two types of pathogenic bacteria, Klebsiella pneumoniae and Serratia marcescens, had been reported as important causes of hospital-acquired infection. Rapid and accurate identification of Klebsiella pneumoniae and Serratia marcescens is vitally impor
Externí odkaz:
https://doaj.org/article/dafab585ac1c4519b87216e8e750876a
Publikováno v:
Science and Engineering of Composite Materials, Vol 26, Iss 1, Pp 402-411 (2019)
BCN coatings with different chemical compositions were prepared using RF magnetron sputtering via adjusting N2 flow. The influence of N2 flow on the bonding structure, mechanical and tribological properties of coating was studied. The structural anal
Externí odkaz:
https://doaj.org/article/c72bca42b73444f9b67f292ffe3af7ad
Machine unlearning is a promising approach to mitigate undesirable memorization of training data in LLMs. However, in this work we show that existing approaches for unlearning in LLMs are surprisingly susceptible to a simple set of targeted relearnin
Externí odkaz:
http://arxiv.org/abs/2406.13356
We study a multi-agent imitation learning (MAIL) problem where we take the perspective of a learner attempting to coordinate a group of agents based on demonstrations of an expert doing so. Most prior work in MAIL essentially reduces the problem to m
Externí odkaz:
http://arxiv.org/abs/2406.04219
Estimates of causal parameters such as conditional average treatment effects and conditional quantile treatment effects play an important role in real-world decision making. Given this importance, one should ensure these estimators are calibrated. Wh
Externí odkaz:
http://arxiv.org/abs/2406.01933