4 papers
Continual Policy Consolidation for Lifelong Robot Learning
Qijun He, Yuxuan Li, Mingqi Yuan +4
Building a generalist robot policy requires continuously integrating new skills while preserving previously acquired behaviors. Directly optimizing a single policy over a growing t…
AlHfN Thin Films with Enhanced Piezoelectric Responses for GHz Surface Acoustic Wave Devices
Laura I. Wagner, Verena Streibel, Esperanza Luna +9
Ternary compounds obtained by alloying wurtzite AlN with transition metals have emerged as promising materials with significantly enhanced piezoelectric characteristics relative to…
Reasoning Scaffolding: Distilling the Flow of Thought from LLMs
Xiangyu Wen, Junhua Huang, Zeju Li +6
The prevailing approach to distilling reasoning from Large Language Models (LLMs)-behavioral cloning from textual rationales-is fundamentally limited. It teaches Small Language Mod…
Large-dimensional Factor Analysis with Weighted PCA
Zhongyuan Lyu, Ming Yuan
Principal component analysis (PCA) is arguably the most widely used approach for large-dimensional factor analysis. While it is effective when the factors are sufficiently strong,…