arXiv subjects

Yikai Dong

Publications and source records attributed to Yikai Dong.

2 recordsLinked to original sources

arXiv2026

EEG Benchmarking Needs a Task Specification Layer: NeuroDoc for Rulebook-Guided, Executable Benchmark Construction

Electroencephalography (EEG) foundation models increasingly rely on multi-dataset training and evaluation, yet public EEG datasets still lack a shared task specification layer that can turn heterogeneous recordings into reusable benchmark units. Existing standards organize files, metadata, and provenance, but they do not specify EEG tasks under a common language and rulebook, leaving critical task semantics scattered across papers, code, and manual interpretation. We investigate whether heterogeneous public EEG datasets can be standardized through a structured task specification language paired with a shared rulebook. Our methodology represents each benchmark entry as a task document synchronized with an executable task kernel, with the rulebook defining task fields, evidence requirements, document-kernel alignment, review states, and machine-checkable constraints. Using this methodology, we release a community-reviewed EEG benchmark corpus centered on 53 completed and reviewed entries with 245 task definitions spanning diverse paradigms, and we introduce NeuroDoc and NeuroAudit as the operational support layer for rulebook-guided drafting, upgrading, review, amendment, and release management. We further examine whether the resulting benchmark units can be instantiated in a shared downstream setting across four EEG foundation model backbones, providing execution-based evidence for reusable, auditable, and executable EEG benchmarking infrastructure.

cs.LG↗

arXiv2026

LiLIS: A Lightweight Distributed Learned Index Framework for Spatial Decision Analysis

Spatial query and analysis results are often directly applied to decision-making processes such as facility location, proximity resource discovery, accessibility analysis, and risk assessment. Therefore, the efficiency of underlying spatial data access directly impacts the response speed of spatial decision analysis. Existing distributed spatial analysis systems (e.g., Simba, Sedona) already have relatively mature execution frameworks. However, they incur substantial overhead in local index construction and query refinement, especially in read-intensive scenarios. Recent studies have shown that learned indices exhibit considerable retrieval potential in single-machine settings, yet how to integrate them into distributed spatial analysis systems with low modification costs remains unaddressed. In this article, we present LiLIS, a Lightweight distributed Learned Index prototype for Spatial decision analysis. Without modifying existing execution engines, LiLIS integrates machine-learned search strategies with spatial-aware partitioning in a distributed framework, and efficiently supports common spatial queries such as point queries, range queries, $k$-nearest neighbor ($k$NN) queries, and spatial joins. Extensive experiments on both real-world and synthetic datasets demonstrate that LiLIS achieves lower latency across various query types and reduces index construction overhead compared with baseline approaches. These results indicate its potential for improving the responsiveness of read-intensive spatial decision-support workflows.

cs.DB↗