Akshay Mehra

27 papers A* 4A 2C 1Misc 1Journal 17Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
Audio-Visual Continual Test-Time Adaptation without Forgetting.
CoRR
Sarthak Kumar Maharana, Akshay Mehra, Bhavya Ramakrishna, Yunhui Guo, Guan-Ming Su
2025 Misc conf
A Quantitative Metric Selection Approach for Time-series Forecasting Foundation Models.
ICASSP
Hongjie Chen, Akshay Mehra, Josh Kimball, Sungchul Kim
2025 J jnl
DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation.
CoRR
Divyansh Srivastava, Akshay Mehra, Pranav Maneriker, Debopam Sanyal, Vishnu Raj, Vijay Kamarshi, Fan Du, Joshua Kimball
2025 A* conf
DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation.
ICML
Yunbei Zhang, Akshay Mehra, Shuaicheng Niu, Jihun Hamm
2025 J jnl
Measuring Time-Series Dataset Similarity using Wasserstein Distance.
CoRR
Hongjie Chen, Akshay Mehra, Josh Kimball, Ryan A. Rossi
2025 J jnl
Model-agnostic Coreset Selection via LLM-based Concept Bottlenecks.
CoRR
Akshay Mehra, Trisha Mittal, Subhadra Gopalakrishnan, Joshua Kimball
2025 A conf
OT-VP: Optimal Transport-Guided Visual Prompting for Test-Time Adaptation.
WACV
Yunbei Zhang, Akshay Mehra, Jihun Hamm
2024 J jnl
Dynamic Domains, Dynamic Solutions: DPCore for Continual Test-Time Adaptation.
CoRR
Yunbei Zhang, Akshay Mehra, Jihun Hamm
2024 J jnl
OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptation.
CoRR
Yunbei Zhang, Akshay Mehra, Jihun Hamm
2024 A conf
On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization.
WACV
Akshay Mehra, Yunbei Zhang, Bhavya Kailkhura, Jihun Hamm
2024 — conf
Test-time Assessment of a Model's Performance on Unseen Domains via Optimal Transport.
CVPR Workshops
Akshay Mehra, Yunbei Zhang, Jihun Hamm
2024 J jnl
Test-time Assessment of a Model's Performance on Unseen Domains via Optimal Transport.
CoRR
Akshay Mehra, Yunbei Zhang, Jihun Hamm
2024 A* conf
Understanding the Transferability of Representations via Task-Relatedness.
NeurIPS
Akshay Mehra, Yunbei Zhang, Jihun Hamm
2023 J jnl
Analysis of Task Transferability in Large Pre-trained Classifiers.
CoRR
Akshay Mehra, Yunbei Zhang, Jihun Hamm
2023 J jnl
On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization.
CoRR
Akshay Mehra, Yunbei Zhang, Bhavya Kailkhura, Jihun Hamm
2022 — conf
A Spectral View of Randomized Smoothing Under Common Corruptions: Benchmarking and Improving Certified Robustness.
ECCV (4)
Jiachen Sun, Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Dan Hendrycks, Jihun Hamm, Z. Morley Mao
2022 J jnl
On Certifying and Improving Generalization to Unseen Domains.
CoRR
Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Jihun Hamm
2022 J jnl
Understanding the Robustness of Multi-Exit Models under Common Corruptions.
CoRR
Akshay Mehra, Skyler Seto, Navdeep Jaitly, Barry-John Theobald
2021 J jnl
Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines.
CoRR
Jiachen Sun, Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Dan Hendrycks, Jihun Hamm, Z. Morley Mao
2021 A* conf
How Robust Are Randomized Smoothing Based Defenses to Data Poisoning?
CVPR
Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Jihun Hamm
2021 J jnl
Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks.
CoRR
Byunggill Joe, Akshay Mehra, Insik Shin, Jihun Hamm
2021 C conf
Penalty Method for Inversion-Free Deep Bilevel Optimization.
ACML
Akshay Mehra, Jihun Hamm
2021 A* conf
Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning.
NeurIPS
Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Jihun Hamm
2021 J jnl
Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning.
CoRR
Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Jihun Hamm
2020 J jnl
How Robust are Randomized Smoothing based Defenses to Data Poisoning?
CoRR
Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Jihun Hamm
2019 J jnl
Penalty Method for Inversion-Free Deep Bilevel Optimization.
CoRR
Akshay Mehra, Jihun Hamm
2018 J jnl
Fast Interactive Image Retrieval using large-scale unlabeled data.
CoRR
Akshay Mehra, Jihun Hamm, Mikhail Belkin