activity
20242026
collaborators

11 papers

cs.LG2026

TADS: Task-Aware Data Selection for Multi-Task Multimodal Pre-Training

Guanjie Cheng, Boyi Li, Lingyu Sun +4

Large-scale multimodal pre-trained models like CLIP rely heavily on high-quality training data, yet raw web-crawled datasets are often noisy, misaligned, and redundant, leading to…

cs.SE2026

Morphis: SLO-Aware Resource Scheduling for Microservices with Time-Varying Call Graphs

Yu Tang, Hailiang Zhao, Chuansheng Lu +4

Modern microservice systems exhibit continuous structural evolution in their runtime call graphs due to workload fluctuations, fault responses, and deployment activities. Despite t…

cs.CV2025

TrackTeller: Temporal Multimodal 3D Grounding for Behavior-Dependent Object References

Jiahong Yu, Ziqi Wang, Hailiang Zhao +3

Understanding natural-language references to objects in dynamic 3D driving scenes is essential for interactive autonomous systems. In practice, many referring expressions describe…

cs.AI2025

OmniFuser: Adaptive Multimodal Fusion for Service-Oriented Predictive Maintenance

Ziqi Wang, Hailiang Zhao, Yuhao Yang +7

Accurate and timely prediction of tool conditions is critical for intelligent manufacturing systems, where unplanned tool failures can lead to quality degradation and production do…

cs.LG2025

Toward Robust and Efficient ML-Based GPU Caching for Modern Inference

Peng Chen, Jiaji Zhang, Hailiang Zhao +11

In modern GPU inference, cache efficiency remains a major bottleneck, and heuristic policies such as \textsc{LRU} can perform far worse than the offline optimum. Existing learning-…

cs.LG2025

XFMNet: Decoding Cross-Site and Nonstationary Water Patterns via Stepwise Multimodal Fusion for Long-Term Water Quality Forecasting

Ziqi Wang, Hailiang Zhao, Cheng Bao +4

Long-term time-series forecasting is critical for environmental monitoring, yet water quality prediction remains challenging due to complex periodicity, nonstationarity, and abrupt…