5 papers · 1 filter
TrAC: Trace-Conditioned Answer Consistency for Efficient Uncertainty Quantification in LLMs
Dahai Yu, Lin Jiang, Rongchao Xu +1
Large language models (LLMs) can generate fluent reasoning traces that nevertheless lead to incorrect answers, making response-level uncertainty estimation important for abstention…
SymboUQ: Symbolic Uncertainty Quantification for Spatial Reasoning in LLMs
Dahai Yu, Lin Jiang, Rongchao Xu +1
Although large language models (LLMs) can produce fluent spatial reasoning traces, their intermediate relations may fail to support the final conclusion, making token-level confide…
MobiDiff: Semantic-Aware Multi-Channel Discrete Diffusion for Human Mobility Data Generation
Rongchao Xu, Lin Jiang, Dahai Yu +5
Human mobility data are essential for transportation optimization, urban planning, and resource allocation, yet real-world mobility data are costly to collect and difficult to shar…
EnergyMamba: An Uncertainty-Aware Graph-Enhanced Selective State Space Model for Energy Consumption Prediction
Dahai Yu, Rongchao Xu, Lin Jiang +1
Energy consumption prediction is essential for efficient grid management, demand-side optimization, and sustainable energy planning. Although advanced machine learning methods have…
SynHAT: A Two-stage Coarse-to-Fine Diffusion Framework for Synthesizing Human Activity Traces
Rongchao Xu, Lin Jiang, Dahai Yu +2
Human activity traces (HATs) are critical for many applications, including human mobility modeling and point-of-interest (POI) recommendation. However, growing privacy concerns hav…