Publications (10)
TopoGaussian: Inferring Internal Topology Structures from Visual Clues
Xiaoyu Xiong, Changyu Hu, Chunru Lin +3
We present TopoGaussian, a holistic, particle-based pipeline for inferring the interior structure of an opaque object from easily accessible photos and videos as input. Traditional…
3D Concept Grounding on Neural Fields
Yining Hong, Yilun Du, Chunru Lin +2
In this paper, we address the challenging problem of 3D concept grounding (i.e. segmenting and learning visual concepts) by looking at RGBD images and reasoning about paired questi…
GS-Agent: Creating 4D Physical Worlds With Generative Simulation
Hongxin Zhang, Chunru Lin, Junyan Li +3
Creating dynamic and physically realistic 4D worlds from natural language descriptions is both fascinating and challenging. Traditional computer graphics methods rely on manual cre…
LuciBot: Automated Robot Policy Learning from Generated Videos
Xiaowen Qiu, Yian Wang, Jiting Cai +4
Automatically generating training supervision for embodied tasks is crucial, as manual designing is tedious and not scalable. While prior works use large language models (LLMs) or…
UBSoft: A Simulation Platform for Robotic Skill Learning in Unbounded Soft Environments
Chunru Lin, Jugang Fan, Yian Wang +6
It is desired to equip robots with the capability of interacting with various soft materials as they are ubiquitous in the real world. While physics simulations are one of the pred…
RoboWits: Unexpected Challenges for Robotic Creative Problem Solving
Chunru Lin, Hongxin Zhang, Fenghao Yu +5
The ability to reason, adapt, and creatively solve problems under unexpected challenges is essential for robots operating in real-world environments. However, current robotic bench…
DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics
Zhiao Huang, Feng Chen, Yewen Pu +3
Combining gradient-based trajectory optimization with differentiable physics simulation is an efficient technique for solving soft-body manipulation problems. Using a well-crafted…
3D Concept Learning and Reasoning from Multi-View Images
Yining Hong, Chunru Lin, Yilun Du +3
Humans are able to accurately reason in 3D by gathering multi-view observations of the surrounding world. Inspired by this insight, we introduce a new large-scale benchmark for 3D…
DLO-Lab: Benchmarking Deformable Linear Object Manipulations with Differentiable Physics
Junyi Cao, Yian Wang, Ziyan Xiong +3
We address the challenge of enabling robots to manipulate deformable linear objects (DLOs), such as ropes, cables, and rubber bands. Prior work has primarily focused on narrow, tas…
RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills
Chunru Lin, Haotian Yuan, Yian Wang +7
Endowing robots with tool design abilities is critical for enabling them to solve complex manipulation tasks that would otherwise be intractable. While recent generative frameworks…