Arvind Narayanan
5 papers · 2020–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Academic Marathon ยท Sprint
๐
Interdisciplinary Bridge ยท Bronze
๐ฅ
Mega-Team ยท Squad
๐
Trend Setter
Top co-authors
Research topics
Keywords
safe harbor
(2)
generative ai
(1)
red teaming
(1)
societal impact
(1)
data generation
(1)
linear interpolation
(1)
ai evaluation
(1)
model entropy
(1)
hindsight merging
(1)
jailbreak
(1)
account suspensions
(1)
legal reprisal
(1)
coordination
(1)
accountability
(1)
flaw disclosure
(1)
third-party evaluation
(1)
monitoring
(1)
customizability
(1)
misuse vectors
(1)
open foundation models
(1)
Papers
Hindsight Merging: Diverse Data Generation with Language Models
UAI 2025
Position: In-House Evaluation Is Not Enough. Towards Robust Third-Party Evaluation and Flaw Disclosure for General-Purpose AI
ICML 2025
Position: A Safe Harbor for AI Evaluation and Red Teaming
ICML 2024
Position: On the Societal Impact of Open Foundation Models
ICML 2024
REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets
ECCV 2020