Sihui Dai
8 papers · 2020–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (3) π Academic Marathon (5) π Cross-Pollinator (15) πΊοΈ Taxonomy Completionist (10)
π§
Keyword Pioneer
β
The Questioner
Conferences
ICML (3)
NIPS (3)
ACL (1)
ICLR (1)
Top co-authors
Keywords
adversarial robustness
(4)
adversarial example
(2)
threat model
(2)
domain generalization
(1)
model robustness
(1)
weakly supervised learning
(1)
adversarial training
(1)
maximum a posteriori
(1)
multi-class classification
(1)
0-1 loss
(1)
adversarial attack
(1)
convolutional neural network
(1)
inductive bia
(1)
generative feedback
(1)
iterative retrieval
(1)
worst-case robustness
(1)
test-time attack
(1)
variation regularization
(1)
unforeseen attack
(1)
bayesian brain hypothesis
(1)
Papers
ImReasoner: Improving Memory-based Language Models for Reasoning-in-a-Haystack Tasks
ACL 2026
Adapting to Evolving Adversaries with Regularized Continual Robust Training
ICML 2025
Larimar: Large Language Models with Episodic Memory Control
ICML 2024
MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
ICML 2023
Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker
NIPS 2023
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?
ICLR 2022
Formulating Robustness Against Unforeseen Attacks
NIPS 2022
Neural Networks with Recurrent Generative Feedback
NIPS 2020