Sizhe Xu — accepted AI-conference papers

2026

nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding

Boyang Li, Yulin Wu, Sizhe Xu, Nuoxian Huang, Zhonghang Yuan, Shangyi Guo +2

ICML 2026poster

Rotary Position Embedding (RoPE) is widely adopted in Transformer models, yet its extension to high-dimensional domains lacks a unified theoretical formulation. Most existing approaches either apply rotations independently along each axis or mix frequencies empirically, which limits cross-dimensiona…

Cited by 0 Source ↗Scholar ↗

2025

Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency

Renzhao Liang, Sizhe Xu, Chenggang Xie, Jingru Chen, Feiyang Ren, Shu Yang +1

NeurIPS 2025spotlight

Time series forecasting plays a pivotal role in critical domains such as energy management and financial markets. Although deep learning-based approaches (e.g., MLP, RNN, Transformer) have achieved remarkable progress, the prevailing "long-sequence information gain hypothesis" exhibits inherent limi…

Cited by 0 Source ↗code ↗Scholar ↗