Benet Oriol Sàbat

I'm a PhD student at UCLA interested in visual and 3D generative AI.


Current research:
- Multimodal control in image and 3D generation.


Publications.


Previously at:
2024 Amazon Applied Science Intern Training and evaluation of LLaVA-like Visual Language Models.
2023 Amazon Applied Science Intern NeRF-Insert: Local 3D editing with multimodal control signals.
2022 Stanford Research Assistant SALAI-Net. Local ancestry inference and genomic representation learning.
2021 Amazon Applied Science Intern Text-to-speech for Alexa.
2020 IRI Research Intern American Sign Language generation with deep learning.
2019 Telefonica Research Intern Automatic speech recognition and multimodal representation learning.


Education:
2022-Today UCLA PhD, Computer Science.
2019-2021 UPC MSc, Telecommuncations Engineering.
2015-2019 UPC BSc, Telecommuncations Engineering.


Resume

benet@cs.ucla.edu
X
GitHub
Google Scholar