Related papers: KELP: Robust Online Log Parsing Through Evolutiona…

Modern distributed systems produce massive, heterogeneous logs essential for reliability, security, and anomaly detection. Converting these free-form messages into structured templates (log parsing) is challenging due to evolving formats…

A Temporal Knowledge Graph (TKG) is a sequence of KGs corresponding to different timestamps. TKG reasoning aims to predict potential facts in the future given the historical KG sequences. One key of this task is to mine and understand…

In the last decade, an impressive increase in software adaptions has led to a surge in log data production, making manual log analysis impractical and establishing the necessity for automated methods. Conversely, most automated analysis…

Tree-based models have been successfully applied to a wide variety of tasks, including time series forecasting. They are increasingly in demand and widely accepted because of their comparatively high level of interpretability. However, many…

The quest to understand structure-function relationships in networks across scientific disciplines has intensified. However, the optimal network architecture remains elusive, particularly for complex information processing. Therefore, we…

Recent advancements in aligning large language models via reinforcement learning have achieved remarkable gains in solving complex reasoning problems, but at the cost of expensive on-policy rollouts and limited exploration of diverse…

Robust text-to-SQL over complex, real-world databases remains brittle even with modern LLMs: iterative refinement often introduces syntactic and semantic drift, corrections tend to be non-transferable across queries, and naive use of large…

Clustering serves as a vital tool for uncovering latent data structures, and achieving both high accuracy and interpretability is essential. To this end, existing methods typically construct binary decision trees by solving mixed-integer…

Large Language Models (LLMs) have shown unprecedented performance in various real-world applications. However, they are known to generate factually inaccurate outputs, a.k.a. the hallucination problem. In recent years, incorporating…

Deep neural networks, despite their remarkable success, remain fundamentally limited in their ability to perform Continual Learning (CL). While most current methods aim to enhance the capabilities of a single model, Inspired by the…

The majority of data in businesses and industries is stored in tables, databases, and data warehouses. Reasoning with table-structured data poses significant challenges for large language models (LLMs) due to its hidden semantics, inherent…

Log parsing transforms raw logs into structured templates containing constants and variables. It underpins anomaly detection, failure diagnosis, and other AIOps tasks. Current parsers are mostly reactive and log-centric. They only infer…

Predictive modeling on web-scale tabular data with billions of instances and hundreds of heterogeneous numerical features faces significant scalability challenges. These features exhibit anisotropy, heavy-tailed distributions, and…

Semantic operators have increasingly become integrated within data systems to enable processing data using Large Language Models (LLMs). Despite significant recent effort in improving these operators, their accuracy is limited due to a…

Designing high-performing metaheuristics for NP-hard combinatorial optimization problems, such as the Vehicle Routing Problem (VRP), remains a significant challenge, often requiring extensive domain expertise and manual tuning. Recent…

Designing the architecture of modern networked systems requires navigating a large, combinatorial space of hardware, systems, and configuration choices with complex cross-layer interactions. Architects must balance competing objectives such…

Answering complex logical queries on incomplete knowledge graphs (KGs) is a fundamental and challenging task in multi-hop reasoning. Recent work defines this task as an end-to-end optimization problem, which significantly reduces the…

Real-time analytics systems employ hybrid data layouts in which data are stored in different formats throughout their lifecycle. Recent data are stored in a row-oriented format to serve OLTP workloads and support high insert rates, while…

Language models generate reasoning sequentially, preventing them from decoupling irrelevant exploration paths during search. We introduce Tree-Structured Language Modeling (TSLM), which uses special tokens to encode branching structure,…

The robustness to distribution changes ensures that NLP models can be successfully applied in the realistic world, especially for information extraction tasks. However, most prior evaluation benchmarks have been devoted to validating…