8 papers
VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation
Siyi Chen, Hugo Hadfield, Alex Zook +9
Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes while adaptively planning, executing, monitoring, and…
SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL
Siyi Chen, Mikaela Angelina Uy, Chan Hee Song +6
Vision Language Models (VLMs) demonstrate strong qualitative visual understanding, but struggle with metrically precise spatial reasoning required for embodied applications. The ag…
Learning Convex Decomposition via Feature Fields
Yuezhi Yang, Qixing Huang, Mikaela Angelina Uy +1
This work proposes a new formulation to the long-standing problem of convex decomposition through learning feature fields, enabling the first feed-forward model for open-world conv…
Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorization
Yang You, Mikaela Angelina Uy, Jiaqi Han +7
Reverse engineering 3D computer-aided design (CAD) models from images is an important task for many downstream applications including interactive editing, manufacturing, architectu…
Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motion
Junru Lin, Chirag Vashist, Mikaela Angelina Uy +4
Existing dynamic scene interpolation methods typically assume that the motion between consecutive timesteps is small enough so that displacements can be locally approximated by lin…
Monocular Dynamic Gaussian Splatting: Fast, Brittle, and Scene Complexity Rules
Yiqing Liang, Mikhail Okunev, Mikaela Angelina Uy +4
Gaussian splatting methods are emerging as a popular approach for converting multi-view image data into scene representations that allow view synthesis. In particular, there is int…