I did my PhD at VILAB, EPFL supervised by Amir Zamir and Pierre Dillenbourg. My research is on the intersection of computer vision and machine learning and in particular, making models more robust and adaptive. Before that, I did a Master in Machine Learning at the University of Cambridge, with a focus on bayesian methods. In my past life, I was a quant in New York and London and worked on creating systematic investment strategies for equity portfolios (or, a glorified coin flipper).
Publications
Controlled Training Data Generation with Diffusion Models
T. Yeo*, A. Atanov*, H. Benoit^, A. Alekseev^, R. Ray, P. Esmaeil Akhoondi, A. Zamir
ViPer: Visual Personalization of Generative Models via Individual Preference Learning
S. Salehi, M. Shafiei, R. Bachmann, T. Yeo, A. Zamir
🔍 Spotlight
4M: Massively Multimodal Masked Modelling
D. Mizrahi, R. Bachmann, O. F. Kar, T. Yeo, M. Gao, A. Dehghan, A. Zamir
Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback
T. Yeo, O. F. Kar, Z. Sodagar, A. Zamir
Task Discovery: Finding the Tasks that Neural Networks Generalize on
A. Atanov, A. Filatov, T. Yeo, A. Sohmshetty, A. Zamir
🎤 Oral
3D Common Corruptions and Data Augmentation
O. F. Kar, T. Yeo, A. Atanov, A. Zamir
🎤 Oral
🎤 Oral
Robust Learning Through Cross-Task Consistency
A. Zamir*, A. Sax*, T. Yeo, O. F. Kar, N. Cheerla, R. Suri, Z. Cao, J. Malik, L. Guibas
🎤 Oral
Iterative Classroom Teaching
T. Yeo, P. Kamalaruban, A. Singla, A. Merchant, T. Asselborn, L. Faucon, P. Dillenbourg, V. Cevher
Education
EPFL
Ph.D. in Computer Science
Advisor: Amir Zamir
Thesis: Making Computer Vision Models Robust and Adaptive
University of Cambridge
M.Phil. in Machine Learning and Machine Intelligence
Thesis: Bayesian optimization for natural language processing
Experience
Teaching Assistant — EPFL
Spring 2018, 2019, 2020: EE559 Deep Learning
Fall 2019: CS433 Machine Learning
Data Scientist — Shift Technology
Quantitative Researher — UBS
Talks
Controlling Generative Models
Netflix
Rapid Network Adaptation
CVPR'24 Test-Time Adaptation Workshop
Making Computer Vision Models Robust and Adaptive
Qualcomm AI Research
Making Computer Vision Models Robust and Adaptive
Kyutai
Making Machine Learning Models Robust and Adaptive
Google Tech Talk
Making Computer Vision Models Robust and Adaptive
NVIDIA, Deep Learning and Vision
Robustness via Cross-Domain Ensembles
RIKEN TrustML Seminar