Sihui Dai
8 papers · 2020–2026 · 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 ↓+2 more ↓ Show less ↑
🗺️ Taxonomy Completionist (18) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🧬 Topic Evolution
❓
The Questioner
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Keywords
adversarial robustness
(5)
adversarial training
(2)
adversarial attack
(2)
threat model
(2)
adversarial example
(2)
regularization
(1)
model robustness
(1)
weakly supervised learning
(1)
episodic memory
(1)
maximum a posteriori
(1)
multi-class classification
(1)
0-1 loss
(1)
diffusion model
(1)
convolutional neural network
(1)
inductive bia
(1)
generative adversarial network
(1)
robust accuracy
(1)
fine tuning
(1)
knowledge updating
(1)
generative feedback
(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
Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker
NeurIPS 2023
MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
ICML 2023
Formulating Robustness Against Unforeseen Attacks
NeurIPS 2022
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?
ICLR 2022
Neural Networks with Recurrent Generative Feedback
NeurIPS 2020