Published in EMNLP 2025 (Main Conference, Short), 2025
Short paper on evaluating MLLMs’ logical reasoning over scientific diagram problems.
Recommended citation: Wang, Y. (Fiona) and Kovashka, A., “Probing Logical Reasoning of MLLMs in Scientific Diagrams,” in Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (Short), November 2025.
Download Paper
Published in IEEE ICDL 2025, 2025
Human- and AI-centric analyses of how learners infer a masked word’s meaning from image–text pairs; identifies features correlated with success.
Recommended citation: Wang, Y. (Fiona), Kovashka, A., Fernández, L., Coutanche, M. N., and Wiener, S., “Towards Understanding Ambiguity Resolution in Multimodal Inference of Meaning,” IEEE International Conference on Development and Learning (ICDL), September 2025.
Download Paper
Published in NeurIPS 2024, 2024
Concept-bottleneck models enriched with knowledge priors from medical textbooks/PubMed to improve robustness under domain shifts.
Recommended citation: Yang, Y., Gandhi, M., Wang, Y., Wu, Y., Yao, M. S., Callison-Burch, C., Gee, J. C., and Yatskar, M., “A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis,” Advances in Neural Information Processing Systems 37, 2024.
Download Paper
Published in ACM SIGCOMM 2020, 2020
Camera-side frame filtering to cut bandwidth/compute for real-time video analytics; evaluated on DNN-based detection pipelines.
Recommended citation: Li, Y., Padmanabhan, A., Zhao, P., Wang, Y. (F.), Xu, G. H., and Netravali, R., “Reducto: On-Camera Filtering for Resource-Efficient Real-Time Video Analytics,” in Proceedings of ACM SIGCOMM 2020, pp. 359–376, Aug. 10–14, 2020.
Download Paper