Harold Benoit
Technical Staff @ Liquid AI, building the Transformer Killer.
I also have learning notes that some people find useful.
News:
Experience
,
supervised by Amir Zamir. .
Research,
supervised by Mattia Rigotti. 
. .Original
What I enjoy
- Good engineering, e.g., training deep neural nets and keeping GPUs busy.
- Good research. Previously, I've done more "data-focused" research, exploring scalable ways to identify or synthetize high-quality data with the intent to render models more general and adaptable to new environments.
Publications
|
Controlled Training Data Generation with Diffusion Models
Teresa Yeo*, Andrei Atanov*, Harold Benoit^, Aleksandr Alekseev^, Ruchira Ray, Pooya Akhoondi, Amir Zamir In review, 2024 arXiv / Github / project page We propose a method to generate tailored synthetic training data, i.e., specifically useful for a given supervised model and target deployment domain. We introduce two feedback mechanisms to guide the generation: 1) model-based and 2) target domain-based. |
|
Unraveling the Key Components of OOD Generalization via
Diversification
Harold Benoit*, Liangze Jiang*, Andrei Atanov*, Oğuzhan Fatih Kar, Mattia Rigotti, Amir Zamir ICLR, 2024 arXiv / OpenReview We distill the critical design factors of current state-of-the-art methods (multi-hypotheses/diversification methods) for spurious correlation situations. |