collaborators

5 papers

cs.LG2026

Forecast Collapse in Time-Series Foundation Models

Shu Wan, Miles Ma, Hank Zhu +4

When forecasting hourly returns for 1,000 US equities, we observe an unexpected phenomenon: predictions become nearly flat and show poor stock ranking, as measured by cross-section…

cs.LG2026

The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction

Shu Wan, Abhinav Gorantla, Huan Liu +2

Under standard graphical assumptions, the Markov boundary of a target variable is the smallest set of features that renders every other feature redundant. Once the boundary is obse…

cs.AI2026

DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers

Shu Wan, Saketh Vishnubhatla, Iskander Kushbay +4

Directed Acyclic Graphs (DAGs) are widely used to represent structured knowledge in scientific and technical domains. However, datasets for real-world DAGs remain scarce because co…

cs.CL2026

Causality Guided Representation Learning for Cross-Style Hate Speech Detection

Chengshuai Zhao, Shu Wan, Paras Sheth +3

The proliferation of online hate speech poses a significant threat to the harmony of the web. While explicit hate is easily recognized through overt slurs, implicit hate speech is…

cs.LG2025

CauSTream: Causal Spatio-Temporal Representation Learning for Streamflow Forecasting

Shu Wan, Reepal Shah, John Sabo +2

Streamflow forecasting is crucial for water resource management and risk mitigation. While deep learning models have achieved strong predictive performance, they often overlook und…