Marcin Detyniecki

6 papers · 2019–2025 · 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 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird

Venues

IJCAI (3) ACL (2) ICLR (1)

Top co-authors

Thibault Laugel (4) Vincent Grari (4) Sylvain Lamprier (3) Xavier Renard (2) Christophe Marsala (2) Marie-jeanne Lesot (2) Marco Scialanga (1) Ekaterina Goliakova (1) Tatsunori Hashimoto (1)

Research topics

Machine Learning (5) Artificial Intelligence (4) Core AI (4) Optimization & Theory (3) Application Areas (2) Deep Learning (1) Bayesian & Probabilistic (1) Core Methods (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1)

Keywords

sensitive attribute (2) demographic parity (2) equalized odd (2) optimal transport (1) knowledge editing (1) llm evaluation (1) feature attribution (1) distributionally robust optimization (1) variational autoencoder (1) model explanation (1) counterfactual explanation (1) causal graph (1) prompt variation (1) continuous feature (1) multiple-choice question (1) activation steering (1) adversarial fairness (1) adversarial debiasing (1) large language model (1) metric assessment (1)

Papers

Metric assessment protocol in the context of answer fluctuation on MCQ tasks ACL 2025 SAKE: Steering Activations for Knowledge Editing ACL 2025 On the Fairness ROAD: Robust Optimization for Adversarial Debiasing ICLR 2024 Fairness without the Sensitive Attribute via Causal Variational Autoencoder IJCAI 2022 Fairness-Aware Neural Rényi Minimization for Continuous Features IJCAI 2020 The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations IJCAI 2019