8 papers
Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems
Szymon Pawlonka, MikoÅaj MaÅkiÅski, Jacek MaÅdziuk
Bongard Problems (BPs) provide a challenging testbed for abstract visual reasoning (AVR), requiring models to identify visual concepts fromjust a few examples and describe them in…
Bootstrap Sampling Rate Greater than 1.0 May Improve Random Forest Performance
StanisÅaw Kaźmierczak, Jacek MaÅdziuk
Random forests (RFs) utilize bootstrap sampling to generate individual training sets for each component tree by sampling with replacement, with the sample size typically equal to t…
Reasoning Limitations of Multimodal Large Language Models. A Case Study of Bongard Problems
MikoÅaj MaÅkiÅski, Szymon Pawlonka, Jacek MaÅdziuk
Abstract visual reasoning (AVR) involves discovering shared concepts across images through analogy, akin to solving IQ test problems. Bongard Problems (BPs) remain a key challenge…
Advancing Generalization Across a Variety of Abstract Visual Reasoning Tasks
MikoÅaj MaÅkiÅski, Jacek MaÅdziuk
The abstract visual reasoning (AVR) domain presents a diverse suite of analogy-based tasks devoted to studying model generalization. Recent years have brought dynamic progress in t…
A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning
MikoÅaj MaÅkiÅski, Jacek MaÅdziuk
We study generalization and knowledge reuse capabilities of deep neural networks in the domain of abstract visual reasoning (AVR), employing Raven's Progressive Matrices (RPMs), a…
Modified Adaptive Tree-Structured Parzen Estimator for Hyperparameter Optimization
Szymon Sieradzki, Jacek MaÅdziuk
In this paper, we review hyperparameter optimization methods for machine learning models, with a particular focus on the Adaptive Tree-Structured Parzen Estimator (ATPE) algorithm.…