Akshay Mehra
9 papers · 2021–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (23) ❓ The Questioner
📈
Trend Setter
Top co-authors
Research topics
Machine Learning
(7)
Artificial Intelligence
(5)
Deep Learning
(5)
Application Areas
(5)
Core AI
(3)
Learning Types · Deep Learning
(3)
Learning Types · Machine Learning
(3)
Optimization & Theory
(3)
Learning Paradigms · Artificial Intelligence
(2)
Computer Vision
(1)
Mathematics & Optimization
(1)
Architectures
(1)
Core Methods
(1)
Generation
(1)
Learning Paradigms · Machine Learning
(1)
Keywords
bilevel optimization
(2)
computational efficiency
(2)
domain shift
(2)
data poisoning
(2)
test-time adaptation
(2)
domain generalization
(2)
transfer learning
(1)
domain adaptation
(1)
optimal transport
(1)
unsupervised domain adaptation
(1)
source domain
(1)
target domain
(1)
hyperparameter tuning
(1)
autoregressive model
(1)
theoretical bound
(1)
randomized smoothing
(1)
adversarial defense
(1)
next-token prediction
(1)
knowledge preservation
(1)
visual prompting
(1)
Papers
DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation
CVPR 2026
DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation
ICML 2025
OT-VP: Optimal Transport-Guided Visual Prompting for Test-Time Adaptation
WACV 2025
On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization
WACV 2024
Understanding the Transferability of Representations via Task-Relatedness
NeurIPS 2024
A Spectral View of Randomized Smoothing under Common Corruptions: Benchmarking and Improving Certified Robustness
ECCV 2022
How Robust Are Randomized Smoothing Based Defenses to Data Poisoning?
CVPR 2021
Penalty Method for Inversion-Free Deep Bilevel Optimization
ACML 2021
Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
NeurIPS 2021