13 papers
TimeNet: An Extensible Unified Data Infrastructure for Next-Generation Temporal Foundation Models
Martin Maritsch, Timo Stoffregen, Thomas Kaar +36
Temporal Foundation Models (TFMs) aim to generalize across domains, datasets, and tasks. Yet, their development remains constrained by fragmented, task-specific data formats, annot…
AdaPCLA: Adaptive Prior-Calibrated Logit Adjustment for Long-Tailed Longitudinal EHR Generation
Shuai Cui, Chen Wenxuan, Wenjie Du +3
Generative modeling of longitudinal Electronic Health Records is increasingly important for privacy-preserving research, yet standard autoregressive models tend to underrepresent t…
Signal-Guided Optimization for Machine Unlearning
Xujia Li, Dan Li, Jian Lou +1
Current machine unlearning methods predominantly rely on global, coarse-grained intervention strategies. They lack precise pilot signals to guide the unlearning process and fail to…
Activation Steering Induces Emergent Misalignment: Steering Vector Construction and Comprehensive Evaluation
Qi Cao, Jian Lou, Meiting Liu +4
Activation steering (AS) has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs). AS modulates model behavior in a flexible an…
TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning
Shunyu Wu, Dan Li, Haozheng Ye +6
Assessing the quality of time series (TS) data is fundamental yet inherently challenging due to the multifaceted nature of quality dimensions. Recently, large language models (LLMs…
Exploiting Verification-Generation Gap: Test-Time Reinforcement Learning with Confidence-Conditioned Verification
Jiahui Li, Jianfeng Shan, Wenpei Chen +5
Test-time reinforcement learning has emerged as a promising paradigm for enhancing the complex reasoning abilities of large language models in a completely label-free manner. Despi…
WaveMoE: A Wavelet-Enhanced Mixture-of-Experts Foundation Model for Time Series Forecasting
Shunyu Wu, Jiawei Huang, Weibin Feng +6
Time series foundation models (TSFMs) have recently achieved remarkable success in universal forecasting by leveraging large-scale pretraining on diverse time series data. Compleme…
MsFormer: Enabling Robust Predictive Maintenance Services for Industrial Devices
Jiahui Zhou, Dan Li, Ruibing Jin +5
Providing reliable predictive maintenance is a critical industrial AI service essential for ensuring the high availability of manufacturing devices. Existing deep-learning methods…
Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning
Jiahui Zhou, Dan Li, Boxin Li +6
Time series is a pervasive data type across various application domains, rendering the reasonable solving of diverse time series tasks a long-standing goal. Recent advances in larg…
Lightweight Time Series Data Valuation on Time Series Foundation Models via In-Context Finetuning
Shunyu Wu, Tianyue Li, Yixuan Leng +4
Time series foundation models (TSFMs) have demonstrated increasing capabilities due to their extensive pretraining on large volumes of diverse time series data. Consequently, the q…
Integrating Time Series into LLMs via Multi-layer Steerable Embedding Fusion for Enhanced Forecasting
Zhuomin Chen, Dan Li, Jiahui Zhou +4
Time series (TS) data are ubiquitous across various application areas, rendering time series forecasting (TSF) a fundamental task. With the astounding advances in large language mo…
Enhancing LLM Reasoning for Time Series Classification by Tailored Thinking and Fused Decision
Jiahui Zhou, Dan Li, Lin Li +5
The reasoning capabilities of large language models (LLMs) have significantly advanced their performance by enabling in-depth understanding of diverse tasks. With growing interest…
Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense
Jiawen Zhang, Kejia Chen, Lipeng He +7
Large Language Models (LLMs) have showcased remarkable capabilities across various domains. Accompanying the evolving capabilities and expanding deployment scenarios of LLMs, their…