Martin Pawelczyk
12 papers · 2020–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) 🏃 Academic Marathon (5)
🐝
Cross-Pollinator
(5)
🏆
Keyword Champion
🏆
Grand Slam
💎
Century Club
(11)
⚡
Prolific Year
(5)
Conferences
ICLR (4)
AISTATS (2)
NIPS (2)
AAAI (1)
ACL (1)
ICML (1)
UAI (1)
Top co-authors
Research topics
Keywords
counterfactual explanation
(3)
membership inference
(2)
stochastic gradient descent
(1)
benchmark evaluation
(1)
adversarial robustness
(1)
decision making
(1)
data augmentation
(1)
explainable ai
(1)
feature attribution
(1)
theoretical analysis
(1)
model interpretability
(1)
data privacy
(1)
model training
(1)
adversarial example
(1)
training data privacy
(1)
privacy protection
(1)
weak-to-strong generalization
(1)
privacy leakage
(1)
sparse explanation
(1)
privacy guarantee
(1)
Papers
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
ACL 2026
Machine Unlearning Fails to Remove Data Poisoning Attacks
ICLR 2025
In-Context Unlearning: Language Models as Few-Shot Unlearners
ICML 2024
I Prefer Not to Say: Protecting User Consent in Models with Optional Personal Data
AAAI 2024
Language Models are Realistic Tabular Data Generators
ICLR 2023
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse
ICLR 2023
Gaussian Membership Inference Privacy
NIPS 2023
On the Privacy Risks of Algorithmic Recourse
AISTATS 2023
On the Trade-Off between Actionable Explanations and the Right to be Forgotten
ICLR 2023
OpenXAI: Towards a Transparent Evaluation of Model Explanations
NIPS 2022
Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis
AISTATS 2022
On Counterfactual Explanations under Predictive Multiplicity
UAI 2020