Piotr Sankowski
9 papers · 2015–2025 · 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 ↓
🌍
Conference Polyglot · Silver
🏃
Academic Marathon · Half
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
Top co-authors
Research topics
Artificial Intelligence
(7)
Core AI
(7)
Machine Learning
(5)
Application Areas
(3)
Learning Types
(2)
Deep Learning
(1)
Knowledge & Reasoning
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Architectures
(1)
Core Methods
(1)
Generation
(1)
Mathematics
(1)
Optimization
(1)
Reasoning
(1)
Keywords
scaling law
(2)
shapley value
(2)
mixture of expert
(2)
feature importance
(2)
large language model
(2)
tree ensemble
(1)
instruction following
(1)
model robustness
(1)
maximum flow
(1)
discrete optimization
(1)
tree models
(1)
parametric optimization
(1)
content moderation
(1)
decision tree
(1)
model explanation
(1)
model interpretability
(1)
feature attribution
(1)
robustness evaluation
(1)
dense model
(1)
text generation
(1)
Papers
Accurate Estimation of Feature Importance Faithfulness for Tree Models
AAAI 2025
Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient
ICML 2025
Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery
ICML 2025
Wait, that’s not an option: LLMs Robustness with Incorrect Multiple-Choice Options
ACL 2025
LLM generated responses to mitigate the impact of hate speech
EMNLP 2024
Scaling Laws for Fine-Grained Mixture of Experts
ICML 2024
Improved feature importance computation for tree models based on the Banzhaf value
UAI 2022
Decomposable Submodular Function Minimization via Maximum Flow
ICML 2021
Revenue Maximization Envy-Free Pricing for Homogeneous Resources
IJCAI 2015