Skip to content

Author

Xu-Heng Li

4 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

High-Probability Regret Bounds for Feel-Good Thompson Sampling

Feel-good Thompson sampling (FGTS) augments the posterior of vanilla Thompson sampling with an exploration term that favors reward functions with high predicted optimal values. This modification achieves minimax-optimal regret up to logarithmic factors in linear contextual bandits, but existing analyses of its two stan...

Xu-Heng Li, Qing-Yue Zhao, Quan-Quan Gu · 0 citations
#machine learning Preprint Oct 2026

Muon Learns Facts Better: Understanding the Role of Spectral Orthogonalization

The Muon optimizer applies spectral orthogonalization to matrix-valued updates and has shown strong performance in large-scale neural network training, yet the mechanisms of this transformation in feature learning remain poorly understood. In this work, we investigate this question through a tractable factual-recall mo...

Xu-Heng Li, Qi-Wei Di, Yuan Cao et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Understanding Off- vs On-Policy Distillation: A Tale of Distinct Training Objectives

On-policy distillation (OPD) learns from teacher feedback on student-generated responses and has shown promise in reducing forgetting relative to supervised fine-tuning (SFT). However, its benefits and fragility remain incompletely understood. We study sequential distillation from multiple teachers, where the student m...

Qi-Wei Di, Xu-Heng Li, Kaixuan Ji et al. · 0 citations
#machine learning Preprint Sep 2026

Saturation-Insensitive Dueling Bandits with General Function Approximation

SI-CDB is introduced, an algorithm that selects opponent arms using a carefully designed heuristic for arm selection that enables saturation-insensitive reward learning and recovers the near-optimal dependence for linear reward classes, eliminating the unfavorable $1/\sigma'(\cdot)$ factor.

Cheng-Gong Zhang, Xu-Heng Li, Qi-Wei Di et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.