Publications

Beyond Shadow Weights: Quantization-Aware Training as Quantized-Endpoint Descent

Sheng-An Xu, Hanyang Li, Jianhao Ma, Ying Cui.

Preprint, arXiv:2609.21834.

arXiv

Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update

Yu-Jie Zhang, Sheng-An Xu, Peng Zhao, Masashi Sugiyama.

Advances in Neural Information Processing Systems 38 (NeurIPS 2025), San Diego, California.

arXiv