activity
20242026
collaborators

7 papers

cs.AI2026

What Drives Interactive Improvement from Feedback?

Bartłomiej Cupiał, Jan Łojek, Mikołaj Garstecki +3

We study when natural-language feedback produces improvement beyond the gains obtainable from repeated attempts alone. In multi-turn language agent setting, higher final accuracy c…

cs.LG2026

When Does Non-Uniform Replay Matter in Reinforcement Learning?

Michal Korniak, Mikołaj Czarnecki, Yarden As +3

Modern off-policy reinforcement learning algorithms often rely on simple uniform replay sampling and it remains unclear when and why non-uniform replay improves over this strong ba…

cs.CL2025

Structured Packing in LLM Training Improves Long Context Utilization

Konrad Staniszewski, Szymon Tworkowski, Sebastian Jaszczur +4

Recent advancements in long-context large language models have attracted significant attention, yet their practical applications often suffer from suboptimal context utilization. T…

cs.LG2025

What Matters in Hierarchical Search for Combinatorial Reasoning Problems?

Michał Zawalski, Gracjan Góral, Michał Tyrolski +5

Efficiently tackling combinatorial reasoning problems, particularly the notorious NP-hard tasks, remains a significant challenge for AI research. Recent efforts have sought to enha…

cs.LG2024

Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control

Michal Nauman, Mateusz Ostaszewski, Krzysztof Jankowski +2

Sample efficiency in Reinforcement Learning (RL) has traditionally been driven by algorithmic enhancements. In this work, we demonstrate that scaling can also lead to substantial i…

cs.LG2024

Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe

Alicja Ziarko, Albert Q. Jiang, Bartosz Piotrowski +3

Text embeddings are essential for many tasks, such as document retrieval, clustering, and semantic similarity assessment. In this paper, we study how to contrastively train text em…