MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning

NeurIPSSpotlight2025

Authors
Jinkun Hao, Naifu Liang, Zhen Luo, Xudong XU, Weipeng Zhong, Ran Yi, Yichen Jin, Zhaoyang Lyu, Feng Zheng, Lizhuang Ma, Jiangmiao Pang
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

The ability of robots to interpret human instructions and execute manipulation tasks necessitates the availability of task-relevant tabletop scenes for training…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

reasoning 3d

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive