7 citations · 7 across the 16 of their papers we have counts for
7 papers · 1 filter
Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models
Hao Wang, Licheng Pan, Yuan Lu +7
The design of learning objectives is central to training time-series forecasting models. Existing learning objectives such as mean squared error mostly treat each future step as an…
DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment
Hao Wang, Licheng Pan, Yuan Lu +7
Training time-series forecasting models requires aligning the conditional distribution of model forecasts with that of the label sequence. The standard direct forecast (DF) approac…
Relaxing Probabilistic Latent Variable Models' Specification via Infinite-Horizon Optimal Control
Zhichao Chen, Hao Wang, Licheng Pan +6
In this paper, we address the issue of model specification in probabilistic latent variable models (PLVMs) using an infinite-horizon optimal control approach. Traditional PLVMs rel…
Mixture of Low Rank Adaptation with Partial Parameter Sharing for Time Series Forecasting
Licheng Pan, Zhichao Chen, Haoxuan Li +5
Multi-task forecasting has become the standard approach for time-series forecasting (TSF). However, we show that it suffers from an Expressiveness Bottleneck, where predictions at…
Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary
Licheng Pan, Yongqi Tong, Xin Zhang +3
Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they often refuse to answer legitimate queries--a phenomenon known as overr…
Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
Hao Wang, Licheng Pan, Zhichao Chen +5
Training time-series forecasting models poses unique challenges in loss function design. Most existing approaches adopt temporal mean squared error, but this study reveals two crit…
DeepFilter: A Transformer-style Framework for Accurate and Efficient Process Monitoring
Hao Wang, Zhichao Chen, Licheng Pan +4
The process monitoring task is characterized by stringent demands for accuracy and efficiency. Current transformer-based methods, characterized by self-attention for temporal fusio…