Valentyn Boreiko
5 papers · 2022–2025 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(14)
❓
The Questioner
Venues
Top co-authors
Research topics
Machine Learning
(3)
Artificial Intelligence
(2)
Computer Vision
(2)
Deep Learning
(2)
Application Areas
(2)
Core AI · Artificial Intelligence
(2)
Learning Types
(2)
Natural Language Processing
(1)
Architectures
(1)
Core AI · Computer Vision
(1)
Generation
(1)
Models
(1)
Optimization & Theory
(1)
Resources & Methods
(1)
Keywords
image classification
(1)
feature learning
(1)
image generation
(1)
interpretability
(1)
deep learning
(1)
diffusion model
(1)
weight decay
(1)
text-to-image model
(1)
image classifier
(1)
counterfactual explanation
(1)
dataset bia
(1)
jailbreak attack
(1)
domain shift
(1)
semantic change
(1)
n-gram language model
(1)
neural network
(1)
systematic error
(1)
spurious feature detection
(1)
cone regularization
(1)
subgroup detection
(1)
Papers
An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks
ICML 2025
How Much Can We Forget about Data Contamination?
ICML 2025
Identification of Systematic Errors of Image Classifiers on Rare Subgroups
ICCV 2023
Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet
ICCV 2023
Diffusion Visual Counterfactual Explanations
NeurIPS 2022