Piotr Piękos

4 papers · 2021–2026 · 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 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (18) 🐣 Hot Topic Early Bird

Venues

ACL (2) ICLR (1) NeurIPS (1)

Top co-authors

Tomasz Odrzygóźdź (1) Łukasz Kuciński (1) Michał Zawalski (1) Jürgen Schmidhuber (1) Ruiying Lu (1) Piotr Miłoś (1) Michał Tyrolski (1) Dandan Guo (1) Damian Stachura (1) Henryk Michalewski (1)

Research topics

Artificial Intelligence (3) Deep Learning (3) Machine Learning (3) Core AI (3) Natural Language Processing (2) Applications (2) Core Methods (2) Learning Types (2) Optimization & Theory (2) Resources & Methods (2) Security & Privacy (1) Application Areas (1) Architectures (1) Models (1) Privacy (1)

Keywords

model compression (1) model-based planning (1) transformer architecture (1) representation learning (1) hierarchical planning (1) mathematical reasoning (1) attention mechanism (1) question answering (1) autoregressive generation (1) language modeling (1) efficient inference (1) data privacy (1) language model (1) mixture of expert (1) compute efficiency (1) parameter efficiency (1) language model fine-tuning (1) pretext task (1) word problem (1) planning horizon (1)

Papers

PDR: A Plug-and-Play Positional Decay Framework for LLM Pre-training Data Detection ACL 2026 SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention NeurIPS 2024 Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search ICLR 2023 Measuring and Improving BERT’s Mathematical Abilities by Predicting the Order of Reasoning. ACL 2021