8 papers
Dual-Cache Latent Space Communication between Heterogeneous Language Models
Jiyao Liu, Qi Zhang, Yaoyi Jia +2
Multi-agent LLM systems split work across models, so answering often requires knowledge that sits in another agent's context: a Sharer has encoded information that a Receiver needs…
PAMF: Prior-Aware Multimodal Fusion for Incomplete Time Series Data
Ziwen Kan, Wugeng Zheng, Tianlong Chen +1
In healthcare, multimodal time series tasks often operate on incomplete observations in practice, for example when ECG segments are lost because electrodes detach or an entire resp…
TRACE: A Temporal Conditional Estimation for Multimodal Time Series Foundation Models
Ziwen Kan, Yishuo Chen, Kecheng Li +7
Time series foundation models (TS-FMs) aim to learn generalizable temporal representations that can be adapted to a wide range of downstream tasks. In real-world multimodal setting…
MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion
Wugeng Zheng, Ziwen Kan, Tianlong Chen +2
Multimodal physiological data powers clinical AI systems from intensive care units to wearable devices, but sensors routinely fail in practice. Two failure modes are common: modali…
Conditional Imputation for Within-Modality Missingness in Multi-Modal Federated Learning
Wugeng Zheng, Ziwen Kan, Katie Wang +2
Multimodal Federated Learning (MMFL) enables privacy-preserving collaborative training, but real-world clinical applications often suffer from within-modality missingness caused by…
Implet: A Post-hoc Subsequence Explainer for Time Series Models
Fanyu Meng, Ziwen Kan, Shahbaz Rezaei +3
Explainability in time series models is crucial for fostering trust, facilitating debugging, and ensuring interpretability in real-world applications. In this work, we introduce Im…