XL
Xinjin Li, Yudi Xia, Calvin Chang Liu, Weiru Lin, Bojun Li, Ziwei Hong, Bolun Zhang, Jinghan Cao, Yu Ma, Tianxin Zhou
· 1 min read
ResearcharXiv cs.LG
GAUDI: Geometry-Aware Diffusion for Calibrated Air-Quality Time-Series Imputation
arXiv:2609.30340v1 Announce Type: new
Abstract: Air-quality sensor outages often create contiguous missing blocks, where side information useful for isolated missingness may be less reliable. We study a block-specific, GAUDI-aligned conditional diffusion imputer that retains temporal and feature processing, visible-value and mask conditioning, variable identity, and diffusion-step information, while suppressing absolute time-position side embeddings. On ItalyAir (13 variables, length-32 windows, nominal 50% block missingness; three archived seeds), this feature-side configuration achieves RMSE 0.340, versus 0.355 for full context and 0.355 for local CSDI. The experiment isolates a geometry-aware conditioning effect under block missingness.
Original source
This story was published by arXiv cs.LG and written by Xinjin Li, Yudi Xia, Calvin Chang Liu, Weiru Lin, Bojun Li, Ziwei Hong, Bolun Zhang, Jinghan Cao, Yu Ma, Tianxin Zhou. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org
