7 papers
Information Bottleneck Learning for Faithful Time Series Forecasting Explanations
Xu Zheng, Wei Cheng, Zhuomin Chen +3
The paper presents IB-Forecast, an interpretable multivariate time-series forecasting model that uses an information bottleneck to generate sparse, faithful explanations of predict…
Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems
Xu Zheng, Zhuomin Chen, Chaohao Lin +4
The paper introduces Trajectory Graph Copilot, a framework that builds probabilistic graphs of past agent trajectories and uses a graph neural network to flag potentially erroneous…
Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs
Xu Zheng, Chaohao Lin, Zhuomin Chen +4
The paper introduces GAMER, a graph‑based action‑centric memory system that stores past reasoning as a dynamic graph and uses temporal‑difference learning to estimate action values…
Uncovering Insights of Compound Flooding with Data-Driven AI
Xu Zheng, Chaohao Lin, Sipeng Chen +7
Compound flooding, driven by nonlinear interactions between multiple hydrometeorological factors, poses a significant challenge to hazard prevention. Existing forecasting approache…
DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL
Esteban Schafir, Xu Zheng, Hojat Allah Salehi +4
Large Language Models (LLMs) have demonstrated remarkable capabilities in translating natural language to SQL, yet existing methods still falter on complex queries requiring multi-…
Towards Structurally Explainable Machine-Generated Text Detection: A Graph-Perspective Framework
Xu Zheng, Zhuomin Chen, Esteban Schafir +7
Despite the success of machine-generated text detectors, the black-box nature remains a critical limitation. Traditional explainability methods rely on token-level saliency, insuff…