4 papers
The Propagation Field: A Geometric Substrate Theory of Deep Learning
Xingrui Gu
Modern deep learning treats neural networks primarily as endpoint functions from inputs to outputs. Inspired by the shift from force to geometry in physics, we ask whether a networ…
Uncertainty-Gated Generative Modeling
Xingrui Gu, Haixi Zhang
Financial time-series forecasting is a high-stakes problem where regime shifts and shocks make point-accurate yet overconfident models dangerous. We propose Uncertainty-Gated Gener…
Conceptual Belief-Informed Reinforcement Learning
Xingrui Gu, Chuyi Jiang, Laixi Shi
Reinforcement learning (RL) has achieved significant success but is hindered by inefficiency and instability, relying on large amounts of trial-and-error data and failing to effici…
CauSkelNet: Causal Representation Learning for Human Behaviour Analysis
Xingrui Gu, Chuyi Jiang, Erte Wang +5
Traditional machine learning methods for movement recognition often struggle with limited model interpretability and a lack of insight into human movement dynamics. This study intr…