Łukasz Struski
10 papers · 2018–2026 · 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 ↓+3 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (16) 🤝 Dynamic Duo (10)
🧬
Topic Evolution
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
Top co-authors
Research topics
Deep Learning
(6)
Machine Learning
(6)
Artificial Intelligence
(4)
Core AI · Artificial Intelligence
(4)
Core Methods
(4)
Architectures
(3)
Optimization & Theory
(3)
Computer Vision
(2)
Techniques
(2)
Mathematics & Optimization
(1)
Core AI · Computer Vision
(1)
Learning Types · Deep Learning
(1)
Learning Types · Machine Learning
(1)
Models
(1)
Optimization
(1)
Keywords
prototypical part
(2)
expected value
(2)
missing data
(2)
feature learning
(1)
model evaluation
(1)
explainable ai
(1)
prototype learning
(1)
inverse functions
(1)
singular value decomposition
(1)
saliency map
(1)
model evidence
(1)
image inpainting
(1)
receptive field
(1)
convolutional neural network
(1)
interpretable model
(1)
variational autoencoder
(1)
computational cost
(1)
gradient-based training
(1)
data imputation
(1)
machine unlearning
(1)
Papers
EPIC: Explanation of Pretrained Image Classification Networks via Prototypes
AAAI 2026
LapSum - One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection
ICML 2025
SEMU: Singular Value Decomposition for Efficient Machine Unlearning
ICML 2025
Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations
AAAI 2024
Bounding Evidence and Estimating Log-Likelihood in VAE
AISTATS 2023
ProtoSeg: Interpretable Semantic Segmentation With Prototypical Parts
WACV 2023
SONGs: Self-Organizing Neural Graphs
WACV 2023
Interpretable Image Classification with Differentiable Prototypes Assignment
ECCV 2022
MisConv: Convolutional Neural Networks for Missing Data
WACV 2022
Processing of missing data by neural networks
NeurIPS 2018