Akshay Mehra

According to our database, Akshay Mehra authored at least 18 papers between 2018 and 2025.

Collaborative distances:

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

2025

Measuring Time-Series Dataset Similarity using Wasserstein Distance.

Hongjie Chen, Akshay Mehra, Josh Kimball, Ryan A. Rossi

CoRR, July, 2025

Model-agnostic Coreset Selection via LLM-based Concept Bottlenecks.

Akshay Mehra, Trisha Mittal, Subhadra Gopalakrishnan, Joshua Kimball

CoRR, February, 2025

OT-VP: Optimal Transport-Guided Visual Prompting for Test-Time Adaptation.

Yunbei Zhang, Akshay Mehra, Jihun Hamm

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025

A Quantitative Metric Selection Approach for Time-series Forecasting Foundation Models.

Hongjie Chen, Akshay Mehra, Josh Kimball, Sungchul Kim

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

2024

Dynamic Domains, Dynamic Solutions: DPCore for Continual Test-Time Adaptation.

Yunbei Zhang, Akshay Mehra, Jihun Hamm

CoRR, 2024

On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization.

Akshay Mehra, Yunbei Zhang, Bhavya Kailkhura, Jihun Hamm

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

Understanding the Transferability of Representations via Task-Relatedness.

Akshay Mehra, Yunbei Zhang, Jihun Hamm

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Test-time Assessment of a Model's Performance on Unseen Domains via Optimal Transport.

Akshay Mehra, Yunbei Zhang, Jihun Hamm

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Analysis of Task Transferability in Large Pre-trained Classifiers.

Akshay Mehra, Yunbei Zhang, Jihun Hamm

CoRR, 2023

2022

Understanding the Robustness of Multi-Exit Models under Common Corruptions.

Akshay Mehra, Skyler Seto, Navdeep Jaitly, Barry-John Theobald

CoRR, 2022

On Certifying and Improving Generalization to Unseen Domains.

Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Jihun Hamm

CoRR, 2022

A Spectral View of Randomized Smoothing Under Common Corruptions: Benchmarking and Improving Certified Robustness.

Jiachen Sun, Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Dan Hendrycks, Jihun Hamm, Z. Morley Mao

Proceedings of the Computer Vision - ECCV 2022, 2022

2021

Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines.

Jiachen Sun, Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Dan Hendrycks, Jihun Hamm, Z. Morley Mao

CoRR, 2021

Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks.

Byunggill Joe, Akshay Mehra, Insik Shin, Jihun Hamm

CoRR, 2021

Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning.

Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Jihun Hamm

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

How Robust Are Randomized Smoothing Based Defenses to Data Poisoning?

Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Jihun Hamm

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Penalty Method for Inversion-Free Deep Bilevel Optimization.

Akshay Mehra, Jihun Hamm

Proceedings of the Asian Conference on Machine Learning, 2021

2018

Fast Interactive Image Retrieval using large-scale unlabeled data.

Akshay Mehra, Jihun Hamm, Mikhail Belkin

CoRR, 2018