Get started
Author

Taku Komura

Observed name: Komura, Taku
Observed institution: University of Hong Kong
OpenAlex ID: A5111568731
MoSAT: Human Motion Generation from Spatial Audio and Textual Description
2026 · Xu, Shuyang, Dou, Zhiyang, et al. · arXiv (Cornell University)
PDF
MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation
2026 · Zhu, Yifei, Shi, Mingyi, et al. · arXiv (Cornell University)
PDF
Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
2026 · Xu, Rui, Qin, Dafei, et al. · arXiv (Cornell University)
Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
2026 · Xu, Rui, Qin, Dafei, et al. · arXiv (Cornell University)
PDF
EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents
2026 · Wang, Wenjia, Pan, Liang, et al. · arXiv (Cornell University)
PDF
SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokens
2026 · Ghosh, Anindita, Golyanik, Vladislav, et al. · arXiv (Cornell University)
PDF
EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos
2026 · Fu, Hongming, Wang, Wenjia, et al. · arXiv (Cornell University)
PDF
UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors
2026 · Xiaoyan Cong, Zekun Li, et al. · Lecture notes in computer science
PDF
EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation
2025 · Zhang, Libo, Li, Zekun, et al. · arXiv (Cornell University)
PDF
CrossGen: Learning and Generating Cross Fields for Quad Meshing
2025 · Dong, Qiujie, Wang, Jiepeng, et al. · ACM Transactions on Graphics
Works count: 10
Citation count:
H-index:
I10-index:
Year
Topic
Type