12 papers
I2CD: Direct Image-to-Convex Decomposition for Simulation-Ready Collision Geometry
Qian Wang, Liam Merz Hoffmeister, Brian Scassellati +1
Physics simulators and motion planners require convex collision geometry, yet image-to-3D generative models output dense, frequently non-manifold visual meshes. Bridging the two to…
Dexterous Tactile World Model
Ziyao Zeng, Xiatao Sun, Hao Wang +6
World models for manipulation are typically trained from video, yet the events that determine how manipulation unfolds, such as making and releasing contact, are difficult to obser…
Accelerating Visual Policy Learning with Sampling-Based Model Predictive Control
Yilang Liu, Haoxiang You, Qian Wang +2
Learning visual policies for locomotion and manipulation requires coordinating contact with the environment and can incur substantial computation and GPU memory costs. First-order…
Decoupling Vision, Language, and Action for Efficient Multi-Task Robot Policies
Xiatao Sun, Chen Liang, Ziyao Zeng +5
Vision-Language-Action (VLA) policies commonly run Vision-Language Model (VLM) backbones with billions of parameters at every policy inference, which costs latency and energy. We r…
Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models
Xiatao Sun, Yuan Zhuang, Mateo Sanchez Lopez Negrete +9
Robotic foundation models still need task-specific fine-tuning before deployment, and the fine-tuned policies often break under modest changes in scene layout, lighting, or nearby…
Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization
Chen Liang, Xiatao Sun, Qian Wang +1
Zeroth-Order (ZO) optimization is pivotal for scenarios where backpropagation is unavailable, such as memory-constrained on-device learning and black-box optimization. However, exi…
Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient
Haoxiang You, Yilang Liu, Davis Zong +5
We present the stochastic decoupled policy gradient (SDPG), a lightweight visual reinforcement learning (RL) method that trains diverse visuomotor control policies end-to-end withi…
Subsecond 3D Mesh Generation for Robot Manipulation
Qian Wang, Omar Abdellall, Tony Gao +2
3D meshes are a fundamental representation widely used in computer science and engineering. In robotics, they are particularly valuable because they capture objects in a form that…
Robust and Efficient MuJoCo-based Model Predictive Control via Web of Affine Spaces Derivatives
Chen Liang, Daniel Rakita
MuJoCo is a powerful and efficient physics simulator widely used in robotics. One common way it is applied in practice is through Model Predictive Control (MPC), which uses repeate…
Mesh RAG: Retrieval Augmentation for Autoregressive Mesh Generation
Xiatao Sun, Chen Liang, Qian Wang +1
3D meshes are a critical building block for applications ranging from industrial design and gaming to simulation and robotics. Traditionally, meshes are crafted manually by artists…
Coherence-based Approximate Derivatives via Web of Affine Spaces Optimization
Daniel Rakita, Chen Liang, Qian Wang
Computing derivatives is a crucial subroutine in computer science and related fields as it provides a local characterization of a function's steepest directions of ascent or descen…
ad-trait: A Fast and Flexible Automatic Differentiation Library in Rust
Chen Liang, Qian Wang, Andy Xu +1
The Rust programming language is an attractive choice for robotics and related fields, offering highly efficient and memory-safe code. However, a key limitation preventing its broa…