Jingyan Xu

Architecturally diverse quantum-classical models fused via Combinatorial Fusion Analysis consistently outperform individual models and literature baselines, unlocking significant accuracy gains on classification tasks.

This work model agents as both arbitrage extractors and Maximal Extractable Value targets, derive the optimal trade size for a risk-averse agent under mean-variance utility with stochastic bridge delays, and formalize multi-chain path selection as a belief-weighted online learning problem whose belief estimates converge under a Robbins-Monro schedule.

ReGrad enables scalable and reversible knowledge injection without the risk of catastrophic forgetting, outperforming traditional methods in both general and domain-specific tasks.

TrustMargin achieves better answer quality by resolving conflicts between parametric memory and retrieved evidence without any training overhead.