Ashwinee Panda

According to our database, Ashwinee Panda authored at least 30 papers between 2020 and 2025.

Collaborative distances:

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

2025

Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior.

Daniel Aarao Reis Arturi, Eric Zhang, Andrew Ansah, Kevin Zhu, Ashwinee Panda, Aishwarya Balwani

CoRR, November, 2025

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

Nikita Afonin, Nikita Andriyanov, Nikhil Bageshpura, Kyle Liu, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Alexander Panchenko, Oleg Rogov, Elena Tutubalina, Mikhail Seleznyov

CoRR, October, 2025

Amortized Latent Steering: Low-Cost Alternative to Test-Time Optimization.

Nathan Egbuna, Saatvik Gaur, Sunishchal Dev, Ashwinee Panda, Maheep Chaudhary

CoRR, September, 2025

FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness.

Anand Swaroop, Akshat Nallani, Saksham Uboweja, Adiliia Uzdenova, Michael Nguyen, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Vasu Sharma, Maheep Chaudhary

CoRR, September, 2025

Evaluation Awareness Scales Predictably in Open-Weights Large Language Models.

Maheep Chaudhary, Ian Su, Nikhil Hooda, Nishith Shankar, Julia Tan, Kevin Zhu, Ashwinee Panda, Ryan Lagasse, Vasu Sharma

CoRR, September, 2025

DynaGuard: A Dynamic Guardrail Model With User-Defined Policies.

Monte Hoover, Vatsal Baherwani, Neel Jain, Khalid Saifullah, Joseph Vincent, Chirag Jain, Melissa Kazemi Rad, C. Bayan Bruss, Ashwinee Panda, Tom Goldstein

CoRR, September, 2025

Dense Backpropagation Improves Training for Sparse Mixture-of-Experts.

Ashwinee Panda, Vatsal Baherwani, Zain Sarwar, Benjamin Thérien, Supriyo Chakraborty, Tom Goldstein

CoRR, April, 2025

Analysis of Attention in Video Diffusion Transformers.

Yuxin Wen, Jim Wu, Ajay Jain, Tom Goldstein, Ashwinee Panda

CoRR, April, 2025

LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation.

Juzheng Zhang, Jiacheng You, Ashwinee Panda, Tom Goldstein

CoRR, April, 2025

Using Attention Sinks to Identify and Evaluate Dormant Heads in Pretrained LLMs.

Pedro Sandoval Segura, Xijun Wang, Ashwinee Panda, Micah Goldblum, Ronen Basri, Tom Goldstein, David Jacobs

CoRR, April, 2025

Gemstones: A Model Suite for Multi-Faceted Scaling Laws.

Sean McLeish, John Kirchenbauer, David Yu Miller, Siddharth Singh, Abhinav Bhatele, Micah Goldblum, Ashwinee Panda, Tom Goldstein

CoRR, February, 2025

Continual Pre-training of MoEs: How robust is your router?

Benjamin Thérien, Charles-Étienne Joseph, Zain Sarwar, Ashwinee Panda, Anirban Das, Shi-Xiong Zhang, Stephen Rawls, Sambit Sahu, Eugene Belilovsky, Irina Rish

Trans. Mach. Learn. Res., 2025

Private Fine-tuning of Large Language Models with Zeroth-order Optimization.

Xinyu Tang, Ashwinee Panda, Milad Nasr, Saeed Mahloujifar, Prateek Mittal

Trans. Mach. Learn. Res., 2025

Safety Alignment Should be Made More Than Just a Few Tokens Deep.

Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, Xiao Ma, Subhrajit Roy, Ahmad Beirami, Prateek Mittal, Peter Henderson

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Privacy Auditing of Large Language Models.

Ashwinee Panda, Xinyu Tang, Christopher A. Choquette-Choo, Milad Nasr, Prateek Mittal

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models.

Neel Jain, Aditya Shrivastava, Chen Zhu, Daben Liu, Alfy Samuel, Ashwinee Panda, Anoop Kumar, Micah Goldblum, Tom Goldstein

CoRR, 2024

Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs.

Ashwinee Panda, Berivan Isik, Xiangyu Qi, Sanmi Koyejo, Tsachy Weissman, Prateek Mittal

CoRR, 2024

A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization.

Ashwinee Panda, Xinyu Tang, Saeed Mahloujifar, Vikash Sehwag, Prateek Mittal

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Privacy-Preserving In-Context Learning for Large Language Models.

Tong Wu, Ashwinee Panda, Jiachen T. Wang, Prateek Mittal

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Teach LLMs to Phish: Stealing Private Information from Language Models.

Ashwinee Panda, Christopher A. Choquette-Choo, Zhengming Zhang, Yaoqing Yang, Prateek Mittal

Proceedings of the Twelfth International Conference on Learning Representations, 2024

StructMoE: Structured Mixture of Experts Using Low Rank Experts.

Zain Sarwar, Ashwinee Panda, Benjamin Thérien, Stephen Rawls, Anirban Das, Kartik Balasubramaniam, Berkcan Kapusuzoglu, Shixiong Zhang, Sambit Sahu, Milind Naphade, Supriyo Chakraborty

Proceedings of the NeurIPS Efficient Natural Language and Speech Processing Workshop, 2024

Dense Backpropagation Improves Routing for Sparsely-Gated Mixture-of-Experts.

Ashwinee Panda, Vatsal Baherwani, Zain Sarwar, Benjamin Thérien, Sambit Sahu, Stephen Rawls, Supriyo Chakraborty, Tom Goldstein

Proceedings of the NeurIPS Efficient Natural Language and Speech Processing Workshop, 2024

Visual Adversarial Examples Jailbreak Aligned Large Language Models.

Xiangyu Qi, Kaixuan Huang, Ashwinee Panda, Peter Henderson, Mengdi Wang, Prateek Mittal

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Visual Adversarial Examples Jailbreak Large Language Models.

Xiangyu Qi, Kaixuan Huang, Ashwinee Panda, Mengdi Wang, Prateek Mittal

CoRR, 2023

Differentially Private In-Context Learning.

Ashwinee Panda, Tong Wu, Jiachen T. Wang, Prateek Mittal

CoRR, 2023

Differentially Private Image Classification by Learning Priors from Random Processes.

Xinyu Tang, Ashwinee Panda, Vikash Sehwag, Prateek Mittal

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

DP-RAFT: A Differentially Private Recipe for Accelerated Fine-Tuning.

Ashwinee Panda, Xinyu Tang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal

CoRR, 2022

Neurotoxin: Durable Backdoors in Federated Learning.

Zhengming Zhang, Ashwinee Panda, Linyue Song, Yaoqing Yang, Michael W. Mahoney, Prateek Mittal, Kannan Ramchandran, Joseph Gonzalez

Proceedings of the International Conference on Machine Learning, 2022

SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification.

Ashwinee Panda, Saeed Mahloujifar, Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2020

FetchSGD: Communication-Efficient Federated Learning with Sketching.

Daniel Rothchild, Ashwinee Panda, Enayat Ullah, Nikita Ivkin, Ion Stoica, Vladimir Braverman, Joseph Gonzalez, Raman Arora

Proceedings of the 37th International Conference on Machine Learning, 2020