Our group conducts research on Human-Centered AI, focusing on Image Generative AI, Computer Graphics, Physical AI, Robotic Learning, Human-AI Interaction and Human Augmentation. Our mission is to build foundation models and user interfaces for Human-centered AI to augment human capabilities.
本研究室は北陸先端科学技術大学院大学・AI知性研究領域に所属しています.「人間中心AIのための基盤技術およびそのインタフェース」を開拓し,特に画像生成AI,コンピュータグラフィクス,フィジカルAI,ユーザインタフェースや人間拡張の分野融合研究を行っています.
Degrees: 情報科学・Information Science (IS) and 知識科学・Knowledge Science (KS)

Sketch-guided, Controllable image generation, 3D model generation, and video generation using diffusion models with sketch-based control.

AI-driven architectural design, anime design, fashion design, and content design from multimodal inputs such as sketch and texts.
Physics-guided content generation such as fluid simulation, smoke illustration, and robotic learning with diffusion policy and VLA models.

Supernumerary robotic limbs, soft actuators, compliant mechanisms, and interactive interfaces for creativity support.
Funded by: JST CREST · JST BOOST · JSPS KAKENHI (B) · JSPS KAKENHI Exploratory · OLM Digital Inc. · Live2D Inc. · NEDO · Kayamori Foundation · Nakayama Foundation · NSF IRES
→ Full list on Publications and Google Scholar.
XD
HC
RM
KN
ML
YL
HS
KS
CC
SL
XX
ZW
BH
SY
MK
TZ
XD
JW
RG
TN
SL
JC
JL
NR
AK
WB
ZP
SY
XG
ZL
YH
RM
NF
SL
ZH
YP