References

Wang, Y., Riddell, E., Chow, A., Sedwards, S., & Czarnecki, K. (2026). Mitigating the modality gap: Few-shot out-of-distribution detection with multi-modal prototypes and image bias estimation Presented at the IEEE/CVF/Winter/Conference/on/Applications/of/Computer/Vision conference. Tucson, Arizona, USA. Retrieved from https://openreview.net/pdf?id=tgnTVmRybs

Czarnecki, K. (2026). Public Crash Video Evidence For Adapting Euro Ncap Intersection Scenarios To North America Presented at the International Technical Conference on the Enhanced Safety of Vehicles (ESV) conference. Toronto, Canada: NHTSA. Retrieved from https://static.nhtsa.gov/esv/pdf/ESV/Proceedings/28/ESV26-279.pdf (Original work published 2026)

Choi, Y. M., Ali, A. B., Czarnecki, K., & Shi, F. (2026). The Illusion of Choice: Assessing Impact of Manipulated LLMs Presented at the Second Workshop on Technical AI Governance Research (TAIGR), ICML conference. Seoul, South Korea. Retrieved from https://openreview.net/forum?id=cOru6rrCT3 (Original work published 2026)

Azadani, M. N., Riddell, J., Sedwards, S., & Czarnecki, K. (2026). Rethinking the Mixture of Vision Encoders Paradigm for Enhanced Visual Understanding in Multimodal LLMs Transactions on Machine Learning Research. Retrieved from https://openreview.net/pdf?id=tgnTVmRybs (Original work published 2026)

Badihi, S., Tegegn, M., Riddell, E., Czarnecki, K., & Rubin, J. (2026). Hey, ChatGPT, Look at My Work: Using Conversational AI in Requirements Engineering Education Presented at the International Conference on Software Engineering (ICSE) conference. Rio de Janeiro, Brazil: IEEE. (Original work published 2026)

Riddell, E., Riddell, J., Sun, G., Antkiewicz, M., & Czarnecki, K. (2026). Stalled, Biased, and Confused: Uncovering Reasoning Failures in LLMs for Cloud-Based Root Cause Analysis Presented at the International Conference on AI Foundation Models and Software Engineering (FORGE) conference. https://doi.org/10.1145/3793655.3793732 (Original work published 2026)

Czarnecki, K. (2026). Systematizing The Unusual: A Guideword- And Ontology-Based Method For Road Hazard Identification And Analysis In Driving Automation Safety Assurance (Gobi) And A Hazard Catalog Presented at the International Technical Conference on the Enhanced Safety of Vehicles (ESV) conference. Toronto, Canada: NHTSA. Retrieved from https://static.nhtsa.gov/esv/pdf/ESV/Proceedings/28/ESV26-241.pdf (Original work published 2026)

Wang, Y., Azadani, M. N., Sedwards, S., & Czarnecki, K. (2025). Leo-mini: An efficient multimodal large language model using conditional token reduction and mixture of multi-modal experts Presented at the Conference on Empirical Methods in Natural Language Processing (EMNLP) conference. Suzhou, China. https://doi.org/10.18653/v1/2025.emnlp-main.368 (Original work published 2025)

Berger, T., Mahmoud, W., Zahra, R. A., Vassilevski, I., Burger, A., Ji, W., … Czarnecki, K. (2025). Cost and Benefit of Tracing Features with Embedded Annotations ACM Transactions on Software Engineering and Methodology, 35(4). https://doi.org/10.1145/3746060 (Original work published 2026)

Huang, C., Abdelzad, V., Sedwards, S., & Czarnecki, K. (2025). VADet: Multi-Frame LiDAR 3D Object Detection Using Variable Aggregation Presented at the 2025 IEEE CVF Winter Conference on Applications of Computer Vision (WACV) conference. Tucson, AZ, USA: IEEE. https://doi.org/10.1109/WACV61041.2025.00079 (Original work published 2025)