1 citations · 1 across the 6 of their papers we have counts for
7 papers
Reinforcement Learning with Decomposed Subtasks
Mattie Terzolo, Mikolaj Sacha, Ayan Sinha +1
Group Relative Policy Optimization (GRPO) and related policy-gradient methods for training language model agents collapse an entire multi-turn rollout into a single scalar trajecto…
GraphMatch: Fusing Language and Graph Representations in a Dynamic Two-Sided Work Marketplace
Mikołaj Sacha, Hammad Jafri, Mattie Terzolo +2
Recommending matches in a text-rich, dynamic two-sided marketplace presents unique challenges due to evolving content and interaction graphs. We introduce GraphMatch, a new large-s…
Trustworthy Retrosynthesis: Eliminating Hallucinations with a Diverse Ensemble of Reaction Scorers
Michal Sadowski, Tadija Radusinović, Maria Wyrzykowska +7
Retrosynthesis is one of the domains transformed by the rise of generative models, and it is one where the problem of nonsensical or erroneous outputs (hallucinations) is particula…
Molecule-Edit Templates for Efficient and Accurate Retrosynthesis Prediction
Mikołaj Sacha, Michał Sadowski, Piotr Kozakowski +2
Retrosynthesis involves determining a sequence of reactions to synthesize complex molecules from simpler precursors. As this poses a challenge in organic chemistry, machine learnin…
Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations
Mikołaj Sacha, Bartosz Jura, Dawid Rymarczyk +3
Prototypical parts-based networks are becoming increasingly popular due to their faithful self-explanations. However, their similarity maps are calculated in the penultimate networ…
ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts
Mikołaj Sacha, Dawid Rymarczyk, Łukasz Struski +2
We introduce ProtoSeg, a novel model for interpretable semantic image segmentation, which constructs its predictions using similar patches from the training set. To achieve accurac…
Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits
Mikołaj Sacha, Mikołaj Błaż, Piotr Byrski +5
The central challenge in automated synthesis planning is to be able to generate and predict outcomes of a diverse set of chemical reactions. In particular, in many cases, the most…