8 papers
Accelerating Goal-Conditioned RL Algorithms and Research
MichaÅ Bortkiewicz, WÅadysÅaw PaÅucki, Vivek Myers +4
Self-supervision has the potential to transform reinforcement learning (RL), paralleling the breakthroughs it has enabled in other areas of machine learning. While self-supervised…
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…
What Matters in Hierarchical Search for Combinatorial Reasoning Problems?
MichaŠZawalski, Gracjan Góral, MichaŠTyrolski +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…
RapidDock: Unlocking Proteome-scale Molecular Docking
RafaÅ Powalski, Bazyli Klockiewicz, Maciej JaÅkowski +6
Accelerating molecular docking -- the process of predicting how molecules bind to protein targets -- could boost small-molecule drug discovery and revolutionize medicine. Unfortuna…
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
Maciej WoÅczyk, BartÅomiej CupiaÅ, 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…
Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search
MichaÅ Zawalski, MichaÅ Tyrolski, Konrad Czechowski +6
Complex reasoning problems contain states that vary in the computational cost required to determine a good action plan. Taking advantage of this property, we propose Adaptive Subgo…