SearcharxivSearch

arXiv subjects

Chenggong Wang

Publications and source records attributed to Chenggong Wang.

4 recordsLinked to original sources

WikiKV: Schema-Evolving Path-Indexed Storage for Hierarchical Knowledge Navigation

LLM-curated hierarchical knowledge bases, namely a tree-structured wiki whose nodes summarize an underlying corpus, have become a dominant substrate for retrieval-augmented applications, yet their storage layer is still treated as an implementation detail. This workload is hierarchical, query-intensive, and continuously evolving, and no existing storage model natively captures all three properties at once. We present WikiKV, a path-indexed key-value storage model purpose-built for this workload, comprising three components: (i) a data-driven schema that bootstraps the hierarchy via Intent-Anchored Schema Induction and refines it through Continuous Evolution Operators; (ii) a consistency protocol for the path-indexed storage model that precludes partial-read observations under concurrent offline rewrites without read-path locking; and (iii) a budgeted navigation operator whose search-accelerated routing reduces the expected number of LLM-assisted descent steps from d to O(1) while preserving anytime semantics with progressively refined answers. We evaluate WikiKV through real-world deployment for the WeChat Official Account AI Assistant and benchmark it against diverse baselines on the AuthTrace dataset, where it achieves balanced low per-operator latency across four query operators against relational, graph, and FS backends, and reaches 63.2% end-to-end answer correctness, exceeding multiple RAG baselines, with the gap widening on low- and high-fan-in multi-document questions. Ablation study further confirms the effectiveness of WikiKV's components.

cs.DB

Coupled Ocean-Atmosphere Dynamics in a Machine Learning Earth System Model

Seasonal climate forecasts are socioeconomically important for managing the impacts of extreme weather events and for planning in sectors like agriculture and energy. Climate predictability on seasonal timescales is tied to boundary effects of the ocean on the atmosphere and coupled interactions in the ocean-atmosphere system. We present the Ocean-linked-atmosphere (Ola) model, a high-resolution (0.25°) Artificial Intelligence/ Machine Learning (AI/ML) coupled earth-system model which separately models the ocean and atmosphere dynamics using an autoregressive Spherical Fourier Neural Operator architecture, with a view towards enabling fast, accurate, large ensemble forecasts on the seasonal timescale. We find that Ola exhibits learned characteristics of ocean-atmosphere coupled dynamics including tropical oceanic waves with appropriate phase speeds, and an internally generated El Niño/Southern Oscillation (ENSO) having realistic amplitude, geographic structure, and vertical structure within the ocean mixed layer. We present initial evidence of skill in forecasting the ENSO which compares favorably to the SPEAR model of the Geophysical Fluid Dynamics Laboratory.

physics.ao-ph

Degradation by Exposure of Co-Evaporated CH3NH3PbI3 Thin Films

Degradation of co-evaporated CH3NH3PbI3 thin films was investigated with x-ray photoelectron spectroscopy (XPS) and x-ray diffraction (XRD) as the films were subjected to exposure of oxygen, dry air, ambient, or H2O. The co-evaporated thin films have consistent stoichiometry and crystallinity suitable for detailed surface analysis. The results indicate that CH3NH3PbI3 is not sensitive to oxygen. Even after 10^13 Langmuire (L, one L equals 10^-6 torr sec) oxygen exposure, no O atoms could be found on the surface. The film is not sensitive to dry air as well. A reaction threshold of about 2*10^10 L is found for H2O exposure, below which no CH3NH3PbI3 degradation takes place and the H2O acts as an n-dopant. Above the threshold, the film begins to decompose, and the amount of N and I decrease quickly, leaving the surface with PbI2, amorphous C and O contamination.

cond-mat.mtrl-sci

Degradation of Co-Evaporated Perovskite Thin Film in Air

Methylammonium lead halide perovskites have been developed as highly promising materials to fabricate efficient solar cells in the past few years. The real impact to energy applications relies on the understanding and controlling of the stability of the material. We investigated the degradation of CH3NH3PbI3 by air exposure using x-ray diffraction (XRD), x-ray photoelectron spectroscopy (XPS), and atomic force microscopy (AFM). The stoichiometric sample was grown with co-evaporation of PbI2 and CH3NH3I on a Au coated Si wafer. It was found that the perovskite thin film gradually turned to PbI2 in air, accompanied with complete removal of N and substantial reduction of I. It was also observed that PbI2 crystallization roughened the film and resulted in a partial exposure of the Au substrate.

cond-mat.mtrl-sci