Andrzej Czyżewski

Franciszek Górski, Andrzej Czyżewski

In this work, we present an annotation framework that demonstrates how a multilingual LLM pretrained on a large corpus can be used as a teacher model to distill the expert knowledge needed for tagging medical texts in Polish. This work is part of a larger project called ADMEDVOICE, within which we collected an extensive corpus of medical texts representing five clinical categories - Radiology, Oncology, Cardiology, Hypertension, and Pathology. Using this data, we had to develop a multi-class classifier, but the fundamental problem turned out to be the lack of resources for annotating an adequate number of texts. Therefore, in our solution, we used the multilingual Llama3.1 model to annotate an extensive corpus of medical texts in Polish. Using our limited annotation resources, we verified only a portion of these labels, creating a test set from them. The data annotated in this way were then used for training and validation of 3 different types of classifiers based on the BERT architecture - the distilled DistilBERT model, BioBERT fine-tuned on medical data, and HerBERT fine-tuned on the Polish language corpus. Among the models we trained, the DistilBERT model achieved the best results, reaching an F1 score > 0.80 for each clinical category and an F1 score > 0.93 for 3 of them. In this way, we obtained a series of highly effective classifiers that represent an alternative to large language models, due to their nearly 500 times smaller size, 300 times lower GPU VRAM consumption, and several hundred times faster inference.

Daniel Cieslak, Andrzej Czyzewski

Physics-informed and data-driven surrogates are increasingly used to approximate mechanics-governed flow fields, but the target quantities assigned to such models are not always identifiable from the input variables available at prediction time. We introduce an input-schema identifiability certificate for computational surrogates. Starting from a reduced physical model, the certificate decomposes a target field into components that are measurable from geometry, components that require boundary-condition information, and components identifiable only up to a symmetry quotient. This yields a pre-training audit: it predicts which oracle-channel interventions should reduce error, which should fail, and which ambiguity cannot be removed by changing the architecture, loss, optimizer, or sample size. We instantiate the framework for incompressible tubular flow using a Cosserat-rod reduction, where lumen velocity separates into a mesh-measurable tangent direction, a boundary-condition-dependent magnitude, and a signed-orientation ambiguity. Controlled experiments on patient-specific aortic CFD geometries, analytic Womersley flows, and an advection-diffusion transfer problem confirm the predicted pattern: supplying signed direction collapses angular error to the oracle regime, whereas supplying magnitude without orientation leaves the predicted sign ambiguity and yields 16-33 percent per-node sign flips. The results provide a mechanics-based diagnostic for deciding whether a surrogate modelling task is physically identifiable before training, and expose failure modes that aggregate error metrics can hide.

Daniel Cieślak, Andrzej Czyżewski

Physics-informed machine learning is often assessed by curve error, although engineering use depends on downstream decisions: ranking candidates, avoiding infeasible designs and limiting regret. We introduce pinn-gym, an open benchmark for material-conditioned lattice design that couples a transparent reduced-order crush-and-impact oracle with five printable polymer cards, dimensionless force-response targets and a protocol spanning curve fidelity, physical admissibility, top-k retrieval and mass regret. Across per-material, pooled and cross-material settings, low nRMSE is frequently insufficient to identify useful design selections. Physics-informed losses alter trade-offs rather than monotonically improving all metrics, and dimensionless conditioning improves comparability without making transfer symmetric. The benchmark is not a certified material model; within the released oracle, candidate generator and material cards, pinn-gym provides a reproducible testbed for evaluating PIML surrogates as decision systems rather than curve predictors alone.

Sebastian Cygert, Andrzej Czyzewski

Recent years have seen impressive progress in visual recognition on many benchmarks, however, generalization to the real-world in out-of-distribution setting remains a significant challenge. A state-of-the-art method for robust visual recognition is model ensembling. however, recently it was shown that similarly competitive results could be achieved with a much smaller cost, by using multi-input multi-output architecture (MIMO). In this work, a generalization of the MIMO approach is applied to the task of object detection using the general-purpose Faster R-CNN model. It was shown that using the MIMO framework allows building strong feature representation and obtains very competitive accuracy when using just two input/output pairs. Furthermore, it adds just 0.5\% additional model parameters and increases the inference time by 15.9\% when compared to the standard Faster R-CNN. It also works comparably to, or outperforms the Deep Ensemble approach in terms of model accuracy, robustness to out-of-distribution setting, and uncertainty calibration when the same number of predictions is used. This work opens up avenues for applying the MIMO approach in other high-level tasks such as semantic segmentation and depth estimation.

Sebastian Cygert, Bartłomiej Wróblewski, Karol Woźniak et al.

While recent computer vision algorithms achieve impressive performance on many benchmarks, they lack robustness - presented with an image from a different distribution, (e.g. weather or lighting conditions not considered during training), they may produce an erroneous prediction. Therefore, it is desired that such a model will be able to reliably predict its confidence measure. In this work, uncertainty estimation for the task of semantic segmentation is evaluated under a varying level of domain shift: in a cross-dataset setting and when adapting a model trained on data from the simulation. It was shown that simple color transformations already provide a strong baseline, comparable to using more sophisticated style-transfer data augmentation. Further, by constructing an ensemble consisting of models using different backbones and/or augmentation methods, it was possible to improve significantly model performance in terms of overall accuracy and uncertainty estimation under the domain shift setting. The Expected Calibration Error (ECE) on challenging GTA to Cityscapes adaptation was reduced from 4.05 to the competitive value of 1.1. Further, an ensemble of models was utilized in the self-training setting to improve the pseudo-labels generation, which resulted in a significant gain in the final model accuracy, compared to the standard fine-tuning (without ensemble).

Sebastian Cygert, Andrzej Czyżewski

Model compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a large effect on noisy cases or objects belonging to less frequent classes. It is a crucial problem from the perspective of the models' safety, especially for object detection in the autonomous driving setting, which is considered in this work. It was shown in the paper that the sensitivity of compressed models to different distortion types is nuanced, and some of the corruptions are heavily impacted by the compression methods (i.e., additive noise), while others (blur effect) are only slightly affected. A common way to improve the robustness of models is to use data augmentation, which was confirmed to positively affect models' robustness, also for highly compressed models. It was further shown that while data imbalance methods brought only a slight increase in accuracy for the baseline model (without compression), the impact was more striking at higher compression rates for the structured pruning. Finally, methods for handling data imbalance brought a significant improvement of the pruned models' worst-detected class accuracy.