Avidan Shah

According to our database, Avidan Shah authored at least 4 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training.

Avidan Shah, Jannik Brinkmann, Rico Angell

CoRR, May, 2026

On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation.

Andy Han, Kristina Fujimoto, Avidan Shah, Kiet Nguyen, Kai Xu, Yueh-Han Chen, Ilia Sucholutsky, Rico Angell

CoRR, May, 2026

2025

Stronger Universal and Transferable Attacks by Suppressing Refusals.

David Huang, Avidan Shah, Alexandre Araujo, David A. Wagner, Chawin Sitawarin

Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

2024

Efficient Mitigation of Bus Bunching through Setter-Based Curriculum Learning.

Avidan Shah, Danny Tran, Yuhan Tang

CoRR, 2024