collaborators

6 papers

cs.LG2026

Analyzing and Improving Diffusion Models for Time-Series Data Imputation: A Proximal Recursion Perspective

Zhichao Chen, Hao Wang, Fangyikang Wang +5

Diffusion models (DMs) have shown promise for Time-Series Data Imputation (TSDI); however, their performance remains inconsistent in complex scenarios. We attribute this to two pri…

cs.LG2026

Deep Time-series Forecasting Needs Kernelized Moment Balancing

Licheng Pan, Hao Wang, Haocheng Yang +7

Deep time-series forecasting can be formulated as a distribution balancing problem aimed at aligning the distribution of the forecasts and ground truths. According to Imbens' crite…

eess.SY2025

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…

cs.LG2025

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…

cs.AI2025

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…

cs.AI2025

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…