Ronnachai ‘Tiam’ Jaroensri
About
I am currently a researcher in Google Health working on advancing multimodal capabilities of Gemini, Google's generative AI model. My focus is on developing and improving Gemini's understanding of histopathology concepts. I am particularly interested in how we can utilize its vision-language ability to create a performant system that can interact with users in a more natural way.
Before Google, I completed my PhD study under Professor Freédo Durand at MIT CSAIL, working on using synthetic data to solve various computer vision and signal processing problems. Previously, I attended Stanford University for a bachelor's degree in Physics, and I completed my high school education at Suankularb Wittayalai School in Bangkok, Thailand. 
Projects
Generating Training Data for Denoising Real RGB Images via Camera Pipeline Simulation
Ronnachai Jaroensri, Camille Biscarrat, Miika Aittala, Frédo Durand
arXiv:1904.08825
[Project Page]
[PDF]
[Code]
[Data]
[Training Data]
Learning-based Video Motion Magnification
Tae-Hyun Oh*, Ronnachai Jaroensri*, Changil Kim, Mohamed Elgharib, Frédo Durand, William Freeman, Wojciech Matusik
ECCV 2018 (Oral)
[Project Page]
[PDF]
[Code]
[Data]
*Equal contribution.
On the Importance of Label Quality for Semantic Segmentation
Aleksandar Zlateski*, Ronnachai Jaroensri*, Prafull Sharma, Frédo Durand
CVPR 2018
[PDF]
*Equal contribution.
A Video-Based Method for Automatically Rating Ataxia
Ronnachai Jaroensri*, Amy Zhao*, Guha Balakrishnan, Derek Lo, Jeremy Schmahmann, Frédo Durand, John Guttag
MLHC 2017
[PDF]
*Equal contribution.
