Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Phillip Wallis

Phillip Wallis

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

ML×1NLP×1Crypto×1

Frequent co-authors

Minbeom Kim1×
Lesly Miculicich1×
Bhavana Dalvi Mishra1×
Mihir Parmar1×
Bharath Chandrasekhar1×
Kyomin Jung1×

Research Timeline

2026
LiSA: Lifelong Safety Adaptation via Conservative Policy Induction

LiSA introduces a conservative policy induction framework that enhances fixed AI guardrails by converting sparse, noisy failure reports into reusable, generalized policies, significantly improving safety in real-world deployment.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CLcs.CRRecentMay 14, 2026

LiSA: Lifelong Safety Adaptation via Conservative Policy Induction

Minbeom Kim, Lesly Miculicich, Bhavana Dalvi Mishra, Mihir Parmar +5 more

LiSA introduces a conservative policy induction framework that enhances fixed AI guardrails by converting sparse, noisy failure reports into reusable, generalized policies, significantly improving saf…

View →