I am looking for motivated students to pursue exciting research projects. Each project can lead to a possible top-conference publication! In general, students should satisfy the following prerequisites:

• have some background in Machine Learning and/or (Geometric) Computer Vision,
• know basic mathematics (Linear Algebra, Calculus…),
• have standard scientific coding skills (Python…).

Expert knowledge in specific research areas is NOT required! Students must be motivated, curious to learn new concepts, and not shy from applying theory to practice. Many research topics are available, and can be done in several formats such as a masters' thesis, guided research, or a research assistant position (HiWi). If you are interested in a project, please send me an email!

I am a Postdoctoral Fellow working on Applied Metric Theory (Riemann and Finsler), Geometric Computer Vision, 3D Shape Analysis and Matching, Manifold Analysis, Signal and Image Processing. I was previously a postdoctoral fellow in the Geometric Image Processing (GIP) lab at the Technion-Israel Institute of Technology (Haifa, Israel) under Profs. Ron Kimmel, Alfred Bruckstein, and Michael Lindenbaum. Before that, I was a PhD student in the Computer Science Faculty at the Technion supervised by Profs. Alfred Bruckstein and Michael Lindenbaum. I previously obtained my M.Sc. in Computer Science from the Technion, and my Diplôme d'Ingénieur from École polytechnique (Saclay, France).

Export as PDF, XML, TEX or BIB

2026
Preprints
[]		Harnessing Data Asymmetry: Manifold Learning in the Finsler World (T Dagès, S Weber, D Cremers and R Kimmel), In arXiv preprint arXiv:2603.11396, 2026.  [bibtex] [pdf]
2025
Journal Articles
[]		A model is worth tens of thousands of examples for estimation and thousands for classification (T Dagès, LD Cohen and AM Bruckstein), In Pattern Recognition, Elsevier, volume 157, 2025. ([hal:04764868]) [bibtex] [pdf]
Preprints
[]		Learning Eigenstructures of Unstructured Data Manifolds (R Velich, A Piven, D Bensaïd, D Cremers, T Dagès and R Kimmel), In arXiv preprint arXiv:2512.01103, 2025.  [bibtex] [pdf]
Conference and Workshop Papers
[]		Metric Convolutions: A Unifying Theory to Adaptive Image Convolutions (T Dagès, M Lindenbaum and AM Bruckstein), In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025. ([project page][video]) [bibtex] [pdf] [arXiv:2406.05400]
[]		Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding (T Dagès, S Weber, YWE Lin, R Talmon, D Cremers, M Lindenbaum, AM. Bruckstein and R Kimmel), In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025. ([project page][video]) [bibtex] [pdf] [arXiv:2503.18010]
2024
Journal Articles
[]		Wormhole Loss for Partial Shape Matching (A Bracha, T Dagès and R Kimmel), In Advances in Neural Information Processing Systems, volume 37, 2024. ([project page][video]) [bibtex] [pdf] [arXiv:2410.22899]
Conference and Workshop Papers
[]		On unsupervised partial shape correspondence (A Bracha, T Dagès and R Kimmel), In Proceedings of the Asian Conference on Computer Vision, 2024. ([project page][dataset]) [bibtex] [pdf] [arXiv:2310.14692]
[]		Finsler-Laplace-Beltrami Operators with Application to Shape Analysis (S Weber, T Dagès, M Gao and D Cremers), In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024. ([project page][video]) [bibtex] [pdf] [arXiv:2404.03999]
2023
Preprints
[]		From compass and ruler to convolution and nonlinearity: On the surprising difficulty of understanding a simple CNN solving a simple geometric estimation task (T Dagès, M Lindenbaum and AM Bruckstein), In arXiv preprint arXiv:2303.06638, 2023.  [bibtex] [pdf]
Conference and Workshop Papers
[]		A model is worth tens of thousands of examples (T Dagès, LD Cohen and AM Bruckstein), In International conference on scale space and variational methods in computer vision, 2023.  [bibtex] [pdf] [arXiv:2303.10608]
2022
Journal Articles
[]		Doubly stochastic pairwise interactions for agreement and alignment (T Dagès and AM Bruckstein), In SIAM Journal on Applied Mathematics, SIAM Journal on Applied Mathematics, volume 82, 2022.  [bibtex] [pdf] [arXiv:2012.13727]
2021
Journal Articles
[]		Probabilistic gathering of agents with simple sensors (A Barel, T Dagès, R Manor and AM Bruckstein), In SIAM Journal on Applied Mathematics, SIAM Journal on Applied Mathematics, volume 81, 2021.  [bibtex] [pdf] [arXiv:1902.00294]
Preprints
[]		A Bound on the Edge-Flipping Distance between Triangulations (Revisiting the Proof) (T Dagès and AM Bruckstein), In arXiv preprint arXiv:2106.14408, 2021.  [bibtex] [pdf]
2019
Conference and Workshop Papers
[]		Seeing things in random-dot videos (T Dagès, M Lindenbaum and AM Bruckstein), In Asian Conference on Pattern Recognition, 2019. ([technical report]) [bibtex] [pdf]