Mazda Moayeri
12 papers · 2021–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (24) π§ Keyword Pioneer π Conference Polyglot (7)
π€
Dynamic Duo
(11)
π
Century Club
(12)
π₯
Unstoppable
(5)
Conferences
NIPS (4)
ICLR (3)
CVPR (1)
EMNLP (1)
ICCV (1)
ICML (1)
WACV (1)
Top co-authors
Keywords
image classification
(4)
spurious correlation
(2)
neural network
(2)
adversarial training
(2)
adversarial robustness
(2)
deep neural network
(2)
model robustness
(1)
label noise
(1)
contrastive learning
(1)
feature embedding
(1)
sample complexity
(1)
benchmark evaluation
(1)
feature space
(1)
false positive rate
(1)
data augmentation
(1)
backdoor attack
(1)
distributional robustness
(1)
cross-modal alignment
(1)
self-supervised learning
(1)
semantic segmentation
(1)
Papers
DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors
EMNLP 2025
Rethinking Artistic Copyright Infringements In the Era Of Text-to-Image Generative Models
ICLR 2025
Unearthing Skill-level Insights for Understanding Trade-offs of Foundation Models
ICLR 2025
PRIME: Prioritizing Interpretability in Failure Mode Extraction
ICLR 2024
Data-Centric Debugging: Mitigating Model Failures via Targeted Image Retrieval
WACV 2024
A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
NIPS 2023
Text-To-Concept (and Back) via Cross-Model Alignment
ICML 2023
Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases
NIPS 2023
Hard ImageNet: Segmentations for Objects with Strong Spurious Cues
NIPS 2022
Explicit Tradeoffs between Adversarial and Natural Distributional Robustness
NIPS 2022
A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes
CVPR 2022
Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings
ICCV 2021