This work proposes MUSE, a dependency-aware adaptation framework built on a fully frozen pretrained MAE, which performs lightweight refinement at different encoder depths and explicitly models across-period temporal dependencies and within-period periodic dependencies.
Xin-Ying Cai, Jun-Kai Lu, Yu-Han Zhu et al.· 0 citations
This work proposes QUALS, a large-scale time series corpus equilibrium framework that significantly enhances data efficiency, enabling existing models to achieve superior performance using only a small fraction of the original training data.
Yujie Li, Zezhi Shao, Cheng-Qing Yu et al.· 0 citations
CURE is proposed, a confounder-aware framework for multi-view urban region representation learning that improves predictive performance, remains robust under missing and noisy input views, and provides reliable cross-view integration through shared component separation and context-dependent view weighting.
Sean Bin Yang, Ying Sun, Zong-Yi Xu et al.· 0 citations
This work proposes REFINE, a simple yet effective Representation lEarning Framework that tightly couples road-network-aware generative reconstruction with feedback-driven contrastive learning, enabling the model to capture fine-grained local movement semantics and global spatio-temporal dependencies without manually de...
Sean Bin Yang, Ying Sun, Ji-Lin Hu et al.· Proceedings of the 32nd ACM...· 2 citations
DGCPath is presented, an innovative Distribution-aware Generative Contrastive learning framework for Path representation that establishes a synergistic connection between generative modeling and distributional contrastive learning, enabling the acquisition of robust and transferable feature embeddings.
Sean Bin Yang, Hao Miao, Zong-Yi Xu et al.· Proceedings of the Thirty-Fi...· 1 citation
The notion of a crystal supercell is introduced, which enables more comprehensive explorations of crystal structure and offers evidence that SILVA is capable of outperforming state-of-the-art methods.
Haomin Yu, Ji-Lin Hu, K. Tolborg et al.· ACM Transactions on AI for S...· 0 citations
Time series generation is essential for data augmentation and privacy-preserving analysis across many real-world domains. Recent progress in discrete token modeling~(DTM) has demonstrated strong potential by transforming continuous sequences into discrete representations and performing generation in the latent space. H...
Jiahong Lyu, Hongfan Gao, Wangmeng Shen et al.· Proceedings of the 32nd ACM...· 0 citations
ST-EVO is proposed, which supports dialogue-wise communication scheduling with a compact yet powerful flow-matching based Scheduler to make precise Spatio-Temporal scheduling, and can also perceive the uncertainty of MAS, and possesses self-feedback ability to learn from accumulated experience.
Xingjian Wu, Xvyuan Liu, Junkai Lu et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.