Researcher @SonyAI_global, PhD candidate @HokkaidoUni. Formerly visiting student researcher @StanfordSVL. AI signal processing for 3D & audio. Tweets are my own
I’ll present two papers at #ICML2026:
• GUDA, group-wise data attribution via unlearning
Tue, 2:00–3:45 PM, Hall A
• G2D2, discrete diffusion for inverse problems
TMLR (J2C Certificate), Wed, 5:00–6:45 PM, Hall A
See you in Seoul!
🌟Your static 3D world models are now alive and interactable!
🚀Introducing NeuROK, a neural simulation framework that turns any static 3D object into an interactive 4D asset — no per-category physics, no physical annotations for training.
📄 https://t.co/PSAILjHmZb
🧵 1/n