Yawen Duan
4 papers · 2020–2025 · 4 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 ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
👥
Mega-Team · Squad
Top co-authors
Research topics
Keywords
transfer learning
(1)
neural architecture search
(1)
model safety
(1)
responsible ai
(1)
game playing
(1)
adversarial attack
(1)
benchmark dataset
(1)
zero-shot transfer
(1)
architecture optimization
(1)
vision task
(1)
large language model
(1)
cross-task learning
(1)
leaderboard evaluation
(1)
cross-task search
(1)
adversarial policies
(1)
agent vulnerability
(1)
architecture generalization
(1)
capability safety balance
(1)
Papers
Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability
NAACL 2025
Adversarial Policies Beat Superhuman Go AIs
ICML 2023
TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search
CVPR 2021
CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search
ECCV 2020