Ashwinee Panda

Venues

Frequent coauthors

Papers

1. Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
   ACL 2026 ·

   Nikita Afonin

   DBLP profile ↗ORCID search ↗
2. Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
   NeurIPS 2025 · Ashwinee Panda
3. FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges
   NeurIPS 2025 ·

   Kevin David Hayes

   DBLP profile ↗ORCID search ↗
4. Gemstones: A Model Suite for Multi-Faceted Scaling Laws
   NeurIPS 2025 ·

   Sean McLeish

   DBLP profile ↗ORCID search ↗
5. Privacy Auditing of Large Language Models
   ICLR 2025 · Ashwinee Panda
6. Safety Alignment Should be Made More Than Just a Few Tokens Deep
   ICLR 2025 ·

   Xiangyu Qi

   DBLP profile ↗ORCID search ↗
7. A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
   ICML 2024 · Ashwinee Panda
8. Privacy-Preserving In-Context Learning for Large Language Models
   ICLR 2024 ·

   Tong Wu

   DBLP profile ↗ORCID search ↗
9. Teach LLMs to Phish: Stealing Private Information from Language Models
   ICLR 2024 · Ashwinee Panda
10. Visual Adversarial Examples Jailbreak Aligned Large Language Models
    AAAI 2024 ·

    Xiangyu Qi

    DBLP profile ↗ORCID search ↗