Konrad Staniszewski

According to our database, Konrad Staniszewski authored at least 7 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Inference-Time Hyper-Scaling with KV Cache Compression.

Adrian Lancucki, Konrad Staniszewski, Piotr Nawrot, Edoardo M. Ponti

CoRR, June, 2025

Lightweight Latent Verifiers for Efficient Meta-Generation Strategies.

Bartosz Piotrowski, Witold Drzewakowski, Konrad Staniszewski, Piotr Milos

CoRR, April, 2025

Structured Packing in LLM Training Improves Long Context Utilization.

Konrad Staniszewski, Szymon Tworkowski, Sebastian Jaszczur, Yu Zhao, Henryk Michalewski, Lukasz Kucinski, Piotr Milos

Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024

Analysing The Impact of Sequence Composition on Language Model Pre-Training.

Yu Zhao, Yuanbin Qu, Konrad Staniszewski, Szymon Tworkowski, Wei Liu, Piotr Milos, Yuxiang Wu, Pasquale Minervini

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023

Structured Packing in LLM Training Improves Long Context Utilization.

Konrad Staniszewski, Szymon Tworkowski, Sebastian Jaszczur, Henryk Michalewski, Lukasz Kucinski, Piotr Milos

CoRR, 2023

Focused Transformer: Contrastive Training for Context Scaling.

Szymon Tworkowski, Konrad Staniszewski, Mikolaj Pacek, Yuhuai Wu, Henryk Michalewski, Piotr Milos

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Parity Games of Bounded Tree-Depth.

Konrad Staniszewski

Proceedings of the 31st EACSL Annual Conference on Computer Science Logic, 2023