Open intent classification aims to assign known intents to their corresponding classes while identifying unknown intents. Its success largely relies on accurately annotated data. However, real-world data often contains both in-distribution (IND) noise and out-of-distribution (OOD) noise, which degrades model performanc...
Yan-Hua Li, Xiao-Cao Ouyang, Jie Zhang et al.· Neural Networks· 0 citations
Graph pre-training and prompt tuning provide an effective route to label-efficient node classification by learning transferable backbones and adapting them with lightweight prompts. However, existing pre-train-and-prompt pipelines often generalize poorly across graphs with diverse homophily due to two fundamental limit...
Ting-Ting Li, Yong-Hao Li, Xiang-Kun Wang et al.· Proceedings of the Thirty-Fi...· 0 citations
TS-MTM is proposed, a Temporal-Spectral Masked Time-series Modeling framework that formalizes pretraining within a joint representation space and introduces two synergistic mechanisms: Axial-Period Cross Masking to capture temporal dependencies across phases, and Structure-aware Spectral Magnitude Masking to reconstruc...
Pengcheng Zhang, Xiao-Cao Ouyang, Xin Li et al.· Proceedings of the 32nd ACM...· 0 citations
Time series forecasting is a cornerstone of numerous real-world applications, where prediction accuracy relies on capturing intricate periodic patterns and evolving spectral dynamics. While Masked Time-series Modeling (MTM) has emerged as a powerful self-supervised paradigm, its conventional one-dimensional (1D) formul...
Pengcheng Zhang, Xiaocao Ouyang, Xin Li et al.· Proceedings of the 32nd ACM...· 0 citations
The results show that structured agent memory need not generate an intermediate representation of the past, and Zero-Mem achieves competitive performance while eliminating LLM calls and LLM-token consumption from memory operations.
