6 papers
PG-3DGS: Optimizing 3D Gaussian Splatting to Satisfy Physics Objectives
Zachary Lee, Maxwell Jacobson, Yexiang Xue
Recent advances in Gaussian Splatting have enabled fast, high-fidelity 3D scene generation, yet these methods remain purely visual and lack an understanding of how shapes behave in…
Enforcing Constraints in Generative Sampling via Adaptive Correction Scheduling
Noah Trupin, Yexiang Xue
Hard constraints in generative sampling are typically enforced by projection, applied either once at the end of sampling or after every update. This binary framing overlooks a fund…
Zero-shot Imitation Learning by Latent Topology Mapping
Maxwell J. Jacobson, Yexiang Xue
Imitation learning is effective for training agents when expert demonstrations are available, but collecting demonstrations for every complex task in an environment is costly. We s…
Hypothesis Network Planned Exploration for Rapid Meta-Reinforcement Learning Adaptation
Maxwell Joseph Jacobson, Rohan Menon, John Zeng +1
Meta-Reinforcement Learning (Meta-RL) learns optimal policies across a series of related tasks. A central challenge in Meta-RL is rapidly identifying which previously learned task…
CALM: Contextual Analog Logic with Multimodality
Maxwell J. Jacobson, Corey J. Maley, Yexiang Xue
In this work, we introduce Contextual Analog Logic with Multimodality (CALM). CALM unites symbolic reasoning with neural generation, enabling systems to make context-sensitive deci…
Integrating Symbolic Reasoning into Neural Generative Models for Design Generation
Maxwell Joseph Jacobson, Yexiang Xue
Design generation requires tight integration of neural and symbolic reasoning, as good design must meet explicit user needs and honor implicit rules for aesthetics, utility, and co…