Feng Jiashi
Jiashi Feng is a computer vision and machine learning researcher who currently works at Tencent, having previously served as Research Lead at ByteDance from 2021 to 2025 and Assistant Professor at the National University of Singapore from 2016 to 2021. He is best known for his work on Depth Anything V2 and Depth Anything 3 for monocular depth estimation, as well as contributions including Coordinate Attention, MetaFormer, and Tokens-to-Token ViT. His research spans computer vision, deep learning, and multimodal understanding.
“And Feng Jiashi also came from Microsoft Research Asia... Peng Houwen also joined around late 2024, also from Microsoft Research Asia, also the multimodal direction.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.