OmniPMNet: Bridging discrete and gridded PM10 forecasts via omni-query neural processes

arXiv 2607.11896•44675fb57b8a9ce0d469043b6f1d40655da31b662fad4afa4def4fb7fd0db1d5
ConvCNPDurr-HoyerGaussian-processGaussian-set-convolutionKV-cache-compression','query-agnosticLoRAPM10VAEactivation-compressionair-qualitybattery-degradationchunk-WYdelta-attentionfringe-projection-profilometrygraph-neural-networkhyperdimensional-computinglinear-attentionlogarithmic-encodingphase-controlquantum-computingreflection-theorysensor-fusionspatial-attentionviable-path-entropywrapped-phase

Paper metadata

arXiv ID
2607.11896
Version
Not specified by this published record
Category
Computer Science — Machine Learning (cs.LG)

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

Evidence and limitations

Source ID
arxiv_cs_lg
Record identifier
44675fb57b8a9ce0d469043b6f1d40655da31b662fad4afa4def4fb7fd0db1d5
Enrichment time
2026-07-15T08:52:12Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.

OmniPMNet: Bridging discrete and gridded PM10 forecasts via omni-query neural processes · Baitaphish