Sotabase

Career

· Audit Intern, ALLEN & COOK, INC. CERTIFIED PUBLIC2025–2025
· MSAA Student in Accounting and Analytics, San José State University2025–2026
· Postdoctoral Researcher, UT Austin2025–

Publications (24)

Geometry-aware Instance-reweighted Adversarial Training
International Conference on Learning Representations · 2020
309
cited
DeepInception: Hypnotize Large Language Model to Be Jailbreaker
arXiv.org · 2023
305
cited
Reliable Adversarial Distillation with Unreliable Teachers
International Conference on Learning Representations · 2021
87
cited
Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation
Neural Information Processing Systems · 2023
42
cited
Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?
Neural Information Processing Systems · 2024
40
cited
Understanding the Interaction of Adversarial Training with Noisy Labels
arXiv.org · 2021
30
cited
Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
International Conference on Learning Representations · 2024
23
cited
Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability
International Conference on Machine Learning · 2023
19
cited
Model Inversion Attacks: A Survey of Approaches and Countermeasures
arXiv.org · 2024
17
cited
Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
Neural Information Processing Systems · 2024
16
cited
Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Neural Information Processing Systems · 2022
11
cited
What If the Input is Expanded in OOD Detection?
Neural Information Processing Systems · 2024
8
cited
Combating Exacerbated Heterogeneity for Robust Models in Federated Learning
International Conference on Learning Representations · 2023
7
cited
Decoupling the Class Label and the Target Concept in Machine Unlearning
arXiv.org · 2024
7
cited
Co-Reward: Self-supervised Reinforcement Learning for Large Language Model Reasoning via Contrastive Agreement
arXiv.org · 2025
6
cited
Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models
2025
1
cited
C AN L ARGE L ANGUAGE M ODELS R EASON R OBUSTLY WITH N OISY R ATIONALES ?
Exploring Model Dynamics for Accumulative Poisoning Discovery
International Conference on Machine Learning · 2023
Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Anonymous ACL submission
LiteLMGuard : Seamless and Lightweight On-Device Guardrails for Small Language Models against Quantization Vulnerabilities
Sotabase