Picture for Nevin L. Zhang

Nevin L. Zhang

Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense

Add code
Oct 13, 2024
Figure 1 for Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
Figure 2 for Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
Figure 3 for Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
Figure 4 for Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
Viaarxiv icon

Breaking the mold: The challenge of large scale MARL specialization

Add code
Oct 03, 2024
Viaarxiv icon

TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescription Prediction

Add code
Jul 15, 2024
Figure 1 for TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescription Prediction
Figure 2 for TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescription Prediction
Figure 3 for TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescription Prediction
Figure 4 for TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescription Prediction
Viaarxiv icon

Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bank

Add code
Jan 26, 2024
Viaarxiv icon

Robustness May be More Brittle than We Think under Different Degrees of Distribution Shifts

Add code
Oct 10, 2023
Viaarxiv icon

A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment

Add code
Aug 10, 2023
Viaarxiv icon

A Causal Framework to Unify Common Domain Generalization Approaches

Add code
Jul 13, 2023
Viaarxiv icon

Two-Stage Holistic and Contrastive Explanation of Image Classification

Add code
Jun 10, 2023
Viaarxiv icon

Causal Document-Grounded Dialogue Pre-training

Add code
May 19, 2023
Viaarxiv icon

Contrastive Domain Generalization via Logit Attribution Matching

Add code
May 13, 2023
Viaarxiv icon