13 citations · 22 across the 14 of their papers we have counts for
15 papers
Up and Down the Abstraction Ladder: Code-Based Skills for Language Agents
Bartłomiej Cupiał, Jens Tuyls, Maciej Wołczyk +5
Language agents struggle to act and learn in environments that require long sequences of low-level actions. Code-based abstractions can make these agents more productive by letting…
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…
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…
RapidDock: Unlocking Proteome-scale Molecular Docking
Rafał Powalski, Bazyli Klockiewicz, Maciej Jaśkowski +6
Accelerating molecular docking -- the process of predicting how molecules bind to protein targets -- could boost small-molecule drug discovery and revolutionize medicine. Unfortuna…
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…
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…
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…
tsGT: Stochastic Time Series Modeling With Transformer
Łukasz Kuciński, Witold Drzewakowski, Mateusz Olko +5
Time series methods are of fundamental importance in virtually any field of science that deals with temporally structured data. Recently, there has been a surge of deterministic tr…
Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning
Michal Nauman, Michał Bortkiewicz, Piotr Miłoś +3
Recent advancements in off-policy Reinforcement Learning (RL) have significantly improved sample efficiency, primarily due to the incorporation of various forms of regularization t…
Analysing The Impact of Sequence Composition on Language Model Pre-Training
Yu Zhao, Yuanbin Qu, Konrad Staniszewski +5
Most language model pre-training frameworks concatenate multiple documents into fixed-length sequences and use causal masking to compute the likelihood of each token given its cont…
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
Maciej Wołczyk, Bartłomiej Cupiał, Mateusz Ostaszewski +5
Fine-tuning is a widespread technique that allows practitioners to transfer pre-trained capabilities, as recently showcased by the successful applications of foundation models. How…
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…
Focused Transformer: Contrastive Training for Context Scaling
Szymon Tworkowski, Konrad Staniszewski, Mikołaj Pacek +3
Large language models have an exceptional capability to incorporate new information in a contextual manner. However, the full potential of such an approach is often restrained due…
The Tunnel Effect: Building Data Representations in Deep Neural Networks
Wojciech Masarczyk, Mateusz Ostaszewski, Ehsan Imani +3
Deep neural networks are widely known for their remarkable effectiveness across various tasks, with the consensus that deeper networks implicitly learn more complex data representa…
The Effectiveness of World Models for Continual Reinforcement Learning
Samuel Kessler, Mateusz Ostaszewski, Michał Bortkiewicz +5
World models power some of the most efficient reinforcement learning algorithms. In this work, we showcase that they can be harnessed for continual learning - a situation when the…