Szymon Tworkowski

13 papers A* 4Journal 7Unranked 2
YearRankTypeTitle / Venue / Authors
2025 A* conf
Structured Packing in LLM Training Improves Long Context Utilization.
AAAI
Konrad Staniszewski, Szymon Tworkowski, Sebastian Jaszczur, Yu Zhao, Henryk Michalewski, Lukasz Kucinski, Piotr Milos
2024 — conf
Analysing The Impact of Sequence Composition on Language Model Pre-Training.
ACL (1)
Yu Zhao, Yuanbin Qu, Konrad Staniszewski, Szymon Tworkowski, Wei Liu, Piotr Milos, Yuxiang Wu, Pasquale Minervini
2024 J jnl
Analysing The Impact of Sequence Composition on Language Model Pre-Training.
CoRR
Yu Zhao, Yuanbin Qu, Konrad Staniszewski, Szymon Tworkowski, Wei Liu, Piotr Milos, Yuxiang Wu, Pasquale Minervini
2024 A* conf
Magnushammer: A Transformer-Based Approach to Premise Selection.
ICLR
Maciej Mikula, Szymon Tworkowski, Szymon Antoniak, Bartosz Piotrowski, Albert Q. Jiang, Jin Peng Zhou, Christian Szegedy, Lukasz Kucinski, Piotr Milos, Yuhuai Wu
2023 J jnl
Explaining Competitive-Level Programming Solutions using LLMs.
CoRR
Jierui Li, Szymon Tworkowski, Yingying Wu, Raymond J. Mooney
2023 A* conf
Focused Transformer: Contrastive Training for Context Scaling.
NeurIPS
Szymon Tworkowski, Konrad Staniszewski, Mikolaj Pacek, Yuhuai Wu, Henryk Michalewski, Piotr Milos
2023 J jnl
Focused Transformer: Contrastive Training for Context Scaling.
CoRR
Szymon Tworkowski, Konrad Staniszewski, Mikolaj Pacek, Yuhuai Wu, Henryk Michalewski, Piotr Milos
2023 J jnl
Magnushammer: A Transformer-based Approach to Premise Selection.
CoRR
Maciej Mikula, Szymon Antoniak, Szymon Tworkowski, Albert Qiaochu Jiang, Jin Peng Zhou, Christian Szegedy, Lukasz Kucinski, Piotr Milos, Yuhuai Wu
2023 J jnl
Structured Packing in LLM Training Improves Long Context Utilization.
CoRR
Konrad Staniszewski, Szymon Tworkowski, Sebastian Jaszczur, Henryk Michalewski, Lukasz Kucinski, Piotr Milos
2022 — conf
Hierarchical Transformers Are More Efficient Language Models.
NAACL-HLT (Findings)
Piotr Nawrot, Szymon Tworkowski, Michal Tyrolski, Lukasz Kaiser, Yuhuai Wu, Christian Szegedy, Henryk Michalewski
2022 A* conf
Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers.
NeurIPS
Albert Qiaochu Jiang, Wenda Li, Szymon Tworkowski, Konrad Czechowski, Tomasz Odrzygózdz, Piotr Milos, Yuhuai Wu, Mateja Jamnik
2022 J jnl
Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers.
CoRR
Albert Q. Jiang, Wenda Li, Szymon Tworkowski, Konrad Czechowski, Tomasz Odrzygózdz, Piotr Milos, Yuhuai Wu, Mateja Jamnik
2021 J jnl
Hierarchical Transformers Are More Efficient Language Models.
CoRR
Piotr Nawrot, Szymon Tworkowski, Michal Tyrolski, Lukasz Kaiser, Yuhuai Wu, Christian Szegedy, Henryk Michalewski