8 papers
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…
Hybrid Diffusion Policies with Projective Geometric Algebra for Efficient Robot Manipulation Learning
Xiatao Sun, Yuxuan Wang, Shuo Yang +2
Diffusion policies are a powerful paradigm for robot learning, but their training is often inefficient. A key reason is that networks must relearn fundamental spatial concepts, suc…
RuleSmith: Multi-Agent LLMs for Automated Game Balancing
Ziyao Zeng, Chen Liu, Tianyu Liu +5
Game balancing is a longstanding challenge requiring repeated playtesting, expert intuition, and extensive manual tuning. We introduce RuleSmith, the first framework that achieves…
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…
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…
PRISM-DP: Spatial Pose-based Observations for Diffusion-Policies via Segmentation, Mesh Generation, and Pose Tracking
Xiatao Sun, Yinxing Chen, Daniel Rakita
Diffusion policies generate robot motions by learning to denoise action-space trajectories conditioned on observations. These observations are commonly streams of RGB images, whose…