Nie Lin
Nie Lin is a first-year PhD student in the Computer Vision Group at the Institute of Industrial Science, University of Tokyo, supervised by Professor Yoichi Sato. He is the first author of SiMHand, a similar-hand mining approach for large-scale 3D hand pose pre-training published at ICLR 2025, and the SiMDex framework for selective data curation in vision-language-action model training. He completed his master's degree at the University of Tokyo in 2025 and holds a bachelor's degree in software engineering. He has held research intern positions at Microsoft Research Asia and Sony R&D.
“SiMDex uses only ~1.49M mined samples (<5% of the pool) yet improves the overall success rate from 47.7% to 61.1%”
Source→“The paper's central finding is that *which* human video data you feed a VLA matters more than *how much*. This directly challenges the prevailing 'just scale data' philosophy in robotics.”
Source→“His lab has produced multiple related works including SiMHand (hand pose pre-training)”
Source→“First author who developed the SiMDex framework. Also authored SiMHand (ICLR 2025), a similar mining approach for 3D hand pose pre-training.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.