5 papers
Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow
Yangyang Zhong, Yanmei Gu, Zhengqing Zang +14
Masked Diffusion Language Models (MDLMs) promise parallel token generation and arbitrary-order decoding, yet it remains unclear to what extent current models truly realize these ca…
From Uniform to Adaptive: General Skip-Block Mechanisms for Efficient PDE Neural Operators
Lei Liu, Zhongyi Yu, Hong Wang +4
In recent years, Neural Operators(NO) have gradually emerged as a popular approach for solving Partial Differential Equations (PDEs). However, their application to large-scale engi…
TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction
Zhongyi Yu, Jianqiu Wu, Zhenghao Wu +4
Temporal graph link prediction aims to predict future interactions between nodes in a graph based on their historical interactions, which are encoded in node embeddings. We observe…
MTM: A Multi-Scale Token Mixing Transformer for Irregular Multivariate Time Series Classification
Shuhan Zhong, Weipeng Zhuo, Sizhe Song +3
Irregular multivariate time series (IMTS) is characterized by the lack of synchronized observations across its different channels. In this paper, we point out that this channel-wis…
M-Impute: Mask-guided Representation Learning for Missing Value Imputation
Zhongyi Yu, Zhenghao Wu, Shuhan Zhong +4
Missing values are a common problem that poses significant challenges to data analysis and machine learning. This problem necessitates the development of an effective imputation me…