Filus K, Żarski M.  Submitted.  Beyond Accuracy: Uncovering the Role of Similarity Perception and its Alignment with Semantics in Supervised Learning. arXiv preprint.

Żarski M, Nowaczyk S.  Submitted.  Neuroplasticity-inspired dynamic ANNs for multi-task demand forecasting. arXiv preprint.

Filus K, Romaszewski M, Żarski M.  Submitted.  Semantic Depth Matters: Explaining Errors of Deep Vision Networks through Perceived Class Similarities. arXiv preprint.

Żarski M, Nowaczyk S.  2025.  Balancing Performance and Scalability of Demand Forecasting ML Models. Intelligent Data Analysis XXIII [IDA].

Pojda D, Żarski M, Tomaka A A, Luchowski L.  2025.  dpVision: environment for multimodal images. SoftwareX. 30(102093)

Żarski M, Miszczak J.  2024.  Multi-Step Feature Fusion for Natural Disaster Damage Assessment on Satellite Images. IEEE Access.

Wójcik B, Żarski M, Książek K, Miszczak J, Skibniewski MJ.  2023.  A deep learning method for hard-hat-wearing detection based on head center localization. Bulletin of the Polish Academy of Sciences Technical Sciences. 71 (EA)(6)

Kessler S, Ostaszewski M, Bortkiewicz M, Żarski M, Wołczyk M, Parker-Holder J, Roberts S, Miłoś P.  2023.  The Effectiveness of World Models for Continual Reinforcement Learning. Conference on Lifelong Learning Agents.

Ostrowski M, Blachowski B, Wójcik B, Żarski M, Tauzowski P, Jankowski Ł.  2023.  A framework for computer vision-based health monitoring of a truss structure subjected to unknown excitations. Earthquake Engineering and Engineering Vibration.

Żarski M, Wójcik B, Miszczak J, Blachowski B, Ostrowski M.  2022.  Computer Vision Based Inspection on Post-Earthquake With UAV Synthetic Dataset. IEEE Access. 10

Blachowski B, Ostrowski M, Żarski M, Wójcik B, Tauzowski P, Jankowski L.  2022.  An Efficient Computer Vision-Based Method for Estimation of Dynamic Displacements in Spatial Truss Structures. Workshop on Structural Health Monitoring.

Żarski M, Wójcik B, Książek K, Salamak M, Miszczak J.  2021.  Advances in applicable deep-learning based defect detection. 2nd Workshop on Engineering Optimization – WEO 2021.  (377.77 KB)

Wójcik B, Żarski M, Salamak M, Miszczak J.  2021.  Extracting crack characteristics from RGB-D images. 2nd Workshop on Engineering Optimization – WEO 2021.  (283.77 KB)

Żarski M, Wójcik B, Książek K, Miszczak J.  2021.  Finicky transfer learning—A method of pruning convolutional neural networks for cracks classification on edge devices. Computer-Aided Civil And Infrastructure Engineering. 37(4)

Żarski M, Wójcik B, Miszczak J.  2021.  KrakN: Transfer Learning framework and dataset for infrastructure thin crack detection. SoftwareX. 16

Wójcik B, Żarski M.  2021.  The measurements of surface defect area with an RGB-D camera for a BIM-backed bridge inspection. Bulletin of the Polish Academy of Sciences: Technical Sciences. 69(3)