10 citations · 14 across the 7 of their papers we have counts for
7 papers
Newton to Einstein: Axiom-Based Discovery via Game Design
Pingchuan Ma, Benjamin Tod Jones, Tsun-Hsuan Wang +4
This position paper argues that machine learning for scientific discovery should shift from inductive pattern recognition to axiom-based reasoning. We propose a game design framewo…
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…
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…
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…
DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models
Tsun-Hsuan Wang, Juntian Zheng, Pingchuan Ma +6
Nature evolves creatures with a high complexity of morphological and behavioral intelligence, meanwhile computational methods lag in approaching that diversity and efficacy. Co-opt…
RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation
Yufei Wang, Zhou Xian, Feng Chen +6
We present RoboGen, a generative robotic agent that automatically learns diverse robotic skills at scale via generative simulation. RoboGen leverages the latest advancements in fou…
On the Forward Invariance of Neural ODEs
Wei Xiao, Tsun-Hsuan Wang, Ramin Hasani +4
We propose a new method to ensure neural ordinary differential equations (ODEs) satisfy output specifications by using invariance set propagation. Our approach uses a class of cont…