5 papers
SCALE: Scalable Cross-Attention Learning with Extrapolation for Agentic Workflow Scheduling
Zhifei Xu, Jierui Lan, Zixuan Liang +2
Agentic Large Language Model (LLM) systems decompose complex tasks into workflow Directed Acyclic Graphs (DAGs) whose primitives must be scheduled on heterogeneous clusters. Existi…
Enhanced Estimation Techniques for Certified Radii in Randomized Smoothing
Zixuan Liang
This paper presents novel methods for estimating certified radii in randomized smoothing, a technique crucial for certifying the robustness of neural networks against adversarial p…
Efficient Representations for High-Cardinality Categorical Variables in Machine Learning
Zixuan Liang
High\-cardinality categorical variables pose significant challenges in machine learning, particularly in terms of computational efficiency and model interpretability. Traditional o…
Automating Date Format Detection for Data Visualization
Zixuan Liang
Data preparation, specifically date parsing, is a significant bottleneck in analytic workflows. To address this, we present two algorithms, one based on minimum entropy and the oth…
Harmonizing Metadata of Language Resources for Enhanced Querying and Accessibility
Zixuan Liang
This paper addresses the harmonization of metadata from diverse repositories of language resources (LRs). Leveraging linked data and RDF techniques, we integrate data from multiple…