I started working on advanced mathematical applications designed to solve real-world technology problems during my Postdoc. In the early 2000s I developed an interest in Machine Learning and Biological Data processing. As a Gibbs Assistant Professor at Yale, my research focused on the efficient design of CDMA communication codes and leading the effort of the K.P. White Laboratory in creating a genome-wide signal processing schema for time-series of Microarray gene-expression data of the Drosophila Melanogaster. From 2002, I worked at creating Deep Learning based technologies for large-volume experiments, and over the last four years, I worked for several years as a Science Manager in the Tech Industry, where I designed workflows aimed at optimizing large scale Artificial Intelligence pipelines for the end-to-end mapping and interpretation of customer data.
[1] Stolc V, Gauhar Z, Mason C, Halasz G, van Batenburg MF, Rifkin SA, Hua S, Herreman T, Tongprasit W, Barbano PE, Bussemaker HJ, White KP. A gene expression map for the euchromatic genome of Drosophila melanogaster. Science. 2004;306:655-60. PMID: 15499012.
[2] Ning F, Delhomme D, LeCun Y, Piano F, Bottou L, Barbano PE. Toward automatic phenotyping of developing embryos from videos. IEEE Trans Image Processing. 2005;14:1360-71. PMID: 16190471.
[3] Barbano PE, Spivak M, Flajolet M, Nairn AC, Greengard P, Greengard L. A mathematical tool for exploring the dynamics of biological networks. Proc Natl Acad Sci U S A. 2007;104:19169-74. PMID: 18032599; PMCID: PMC2148263.
A more complete list is here .
.png)
I completed my PhD studies at the Multimedia Laboratory of The Chinese University of Hong Kong in 2025 under the supervision of Prof. Hongsheng Li and Prof. Xiaogang Wang. My main research interests are Deep Learning for Computer Vision applications, Natural Language Processing, Video Recognition, Self-supervised Learning and Multi-modal Large Language Models.
[1] SPHINX: A Mixer of Weights, Visual Embeddings and Image Scales for Multi-modal Large Language Models Ziyi Lin*, Dongyang Liu*, Renrui Zhang*, Peng Gao*, Longtian Qiu*, Han Xiao, Han Qiu, Wenqi Shao, Keqin Chen, Jiaming Han, Siyuan Huang, Yichi Zhang, Xuming He, Yu Qiao, Hongsheng Li European Conference on Computer Vision, 2024
[2] Mimic before reconstruct: Enhancing masked autoencoders with feature mimicking Peng Gao*, Ziyi Lin*, Renrui Zhang, Rongyao Fang, Hongyang Li, Hongsheng Li, Yu Qiao International Journal of Computer Vision, 2024
[3] Retrieving-to-answer: Zero-shot video question answering with frozen large language models Junting Pan*, Ziyi Lin*, Yuying Ge, Xiatian Zhu, Renrui Zhang, Yi Wang, Yu Qiao, Hongsheng Li International Conference on Computer Vision (Workshop), 2023
[4] ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning Junting Pan*, Ziyi Lin*, Xiatian Zhu, Jing Shao, Hongsheng Li Advances in Neural Information Processing Systems, 2022
[5] Frozen clip models are efficient video learners Ziyi Lin, Shijie Geng, Renrui Zhang, Peng Gao, Gerard de Melo, Xiaogang Wang, Jifeng Dai, Yu Qiao, Hongsheng Li European Conference on Computer Vision, 2022
More publications can be found here .
I received my Ph.D. from The University of Alabama in May 2024. Main focus of my research was on radar signal processing and indoor monitoring applications of automotive radars including human activity recognition, hand gesture and sign language recognition. I also worked on automated temporal segmentation of RF data [1], synthetic and simulated RF data generation, separation of raw radar signals from multiple targets [2] and most recently, developed a multi-modal (RF + camera) sign language-controlled Chess game [3].
[1] E. Kurtoğlu, A. C. Gurbuz, E. A. Malaia, D. Griffin, C. Crawford and S. Z. Gurbuz, "ASL Trigger Recognition in Mixed Activity/Signing Sequences for RF Sensor-Based User Interfaces," in IEEE Transactions on Human-Machine Systems, vol. 52, no. 4, pp. 699-712, Aug. 2022.
[2] Kurtoğlu, E., et al.: Boosting multi-target recognition performance with multi-input multi-output radar-based angular subspace projection and multi-view deep neural network. IET Radar Sonar Navig. 17(7), 1115-1128 (2023).
[3] Kurtoğlu, E., et al.: Interactive learning of natural sign language with radar. IET Radar Sonar Navig. 18(8), 1203- 1216 (2024).
I hold a PhD degree from the Electrical and Computer Engineering Department at Duke University. My specialization focuses on leveraging deep learning technologies to enhance medical applications. Throughout my doctoral research, I tackled critical challenges such as label insufficiency and data sharing restrictions—essential for the effective deployment of machine learning models in real-world healthcare settings.
[1] Contrastive Learning for Clinical Outcome Prediction with Partial Data Sources. Meng Xia, Jonathan Wilson, Benjamin Goldstein, Ricardo Henao; ICML (2024). https://pubmed.ncbi.nlm.nih.gov/39148511/
[2] Reliable Active Learning via Influence Functions Meng Xia, Ricardo Henao; TMLR (2023). https://openreview.net/forum?id=dN9YICB6hN¬eId=b7pdOKnto4
[3] Lesion identification and malignancy prediction from clinical dermatological images Meng Xia, Meenal K. Kheterpal, Samantha C. Wong, Christine Park, William Ratliff, Lawrence Carin, Ricardo Henao; Sci Rep 12, 15836 (2022). https://doi.org/10.1038/s41598-022-20168-w
[4] Use of convolutional neural networks in skin lesion analysis using real world image and non-image data Samantha C. Wong, William Ratliff, Meng Xia, Christine Park, Mark Sendak, Suresh Balu, Ricardo Henao, Lawrence Carin and Meenal K. Kheterpal; Frontiers in Medicine (2022). https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2022.946937/full
.png)
I earned a Ph.D. in Data Science in 2024 from New York University, where I worked with Prof. Julia Kempe. My research interests encompass a range of topics in fundamental deep learning including network pruning, data robustness, and the geometry of loss landscapes. I am now working on Deep Learning applications in molecular biology and genomics. Previously, I received a B.S. in Mathematics from the University of Massachusetts Amherst and had internships at Samsung AI, Bloomberg, and IBM.
[1] Vysogorets, A., Ahuja, K., Kempe, J. (2025). "DRoP: Distributionally Robust Data Pruning". The 13th International Conference on Learning Representations, 2025
[2] Vysogorets, A., Ahuja, K., Kempe, J. (2024). "Robust Data Pruning: Uncovering and Overcoming Implicit Bias". DMLR Workshop @ ICLR 2025.
[3] Vysogorets, A., Dawid A., Kempe, J. (2024). "Deconstructing the Goldilocks Zone of Neural Network Initialization". The 41st International Conference on Machine Learning.
[4] Vysogorets, A., Kempe, J. (2023). "Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity". Journal of Machine Learning Research, 24, 99:1-99:23.
[5] Braden, T., Vysogorets, A. (2020). "Kazhdan-Lusztig Polynomials of Matroids Under Deletion". Electronic Journal of Combinatorics, 27, (1).
[6] Vysogorets, A., Gopal, A. (2023). "Towards Efficient Active Learning in NLP via Pretrained Representations". DMLR Workshop @ ICLR 2024.
More information about my work is here .
I completed my PhD in Mathematics at the University of Houston. During my PhD, I mainly focused on integrating model-based and learning-based strategies for Computational Imaging and Biomedical Image Analysis. By integrating conventional model-based techniques, such as compressive sensing and wavelets, with deep learning models, I aimed to improve theoretical understanding and enhance the interpretability of deep learning in practical applications.
[1] MIRE: Matched Implicit Neural Representations. Jayasundara, D., Zhao, H., Labate, D., Patel, V., In: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025).
[2] PIN: Prolate Spheroidal Wave Function-based Implicit Neural Representations. Jayasundara, D., Zhao, H., Labate, D., Patel, V. The Thirteenth International Conference on Learning Representations (ICLR 2025).
[3] Integration of Model- and Learning-Based Methods in Image Restoration. Labate, D., Zhao, H. RICAM series on “Data-driven models in inverse problems” (2024)
[4] Blind Image Inpainting with Sparse Directional Filter Dictionaries for Lightweight CNNs. Schmalfuss, J., Scheurer, E., Zhao, H., Karantzas, N., Bruhn, A., Labate, D. Journal of Mathematical Imaging and Vision (2022).
I received my M.S. and B.S. from the University of Pennsylvania and the University of Minnesota. My current research focuses on real-time animal tracking and pose estimation for laboratory animals. I'm also interested in machine learning applications in Alzheimer's disease research.
[1] Xu, J., Wei, T., Hou, B., Orzechowski, P., Yang, S., Demiris, G., Shen, L. MentalGPT: Harnessing AI for Compassionate Mental Health Support. AMIA 2024 Symposium.
[2] Xu, J., Wei, T., Hou, B., Demiris, G., Shen, L. Revolutionizing Dementia Care: Enhancing Talk Therapy with Fine-Tuned Large Language Models Using GPT Self-Generated Data. AAIC 2024.
[3] Wei, T., Yang, S., Tarzanagh, D. A., Bao, J., Xu, J., Orzechowski, P., Wagenaar, J. B., Long, Q., Shen, L. Clustering Alzheimer’s Disease Subtypes via Similarity Learning and Graph Diffusion. International Conference on Intelligent Biology and Medicine (ICIBM). Tampa, FL, July 2023.
My name is Yuejia Yin. I graduated from New York University (M.S.) and East China Normal University (B.S.). My research interests focus on applying machine learning techniques to medical and biological image analysis. Currently working with Heintz/ Murakami on 3D gene cell segmentation for the whole brain through computer vision. I am also interested in medical image segmentation for the 3D MRI segment. I am also interested in neural signals and worked on electrodermal signals for human emotions.
Xie, Y, Yin, Y. and Wang, Y., Deep Mutual Distillation for Semi-supervised Medical Image Segmentation, MICCAI 2023
I received my B.S. from HSE University in Moscow and am currently pursuing my M.S. degree at NYU. My research focuses on applications of video understanding models for animal behavior analysis.