Ashwinee Panda

机构：Together, University of Maryland, College Park

发表论文 35 篇 · 总被引 257 次 · h-index 6

代表论文

• Visual Adversarial Examples Jailbreak Aligned Large Language Models (2024 · Proceedings of the AAAI Conference on Artificial Intelligence · 被引 115)
• Safety Alignment Should Be Made More Than Just a Few Tokens Deep (2024 · arXiv (Cornell University) · 被引 4)
• Differentially Private Image Classification by Learning Priors from Random Processes (2025 · Journal of Privacy and Confidentiality · 被引 1)
• Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models (2024 · arXiv (Cornell University) · 被引 1)
• Speculating Experts Accelerates Inference for Mixture-of-Experts (2026 · arXiv (Cornell University))
• Speculating Experts Accelerates Inference for Mixture-of-Experts (2026 · arXiv (Cornell University))