8 papers
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
Yicheng Zou, Dongsheng Zhu, Lin Zhu +174
We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancem…
Labels Matter More Than Models: Rethinking the Unsupervised Paradigm in Time Series Anomaly Detection
Zhijie Zhong, Zhiwen Yu, Kaixiang Yang +3
Time series anomaly detection (TSAD) is a critical data mining task often constrained by label scarcity. Consequently, current research predominantly focuses on Unsupervised Time-s…
PathFinder: Advancing Path Loss Prediction for Single-to-Multi-Transmitter Scenario
Zhijie Zhong, Zhiwen Yu, Pengyu Li +3
Radio path loss prediction (RPP) is critical for optimizing 5G networks and enabling IoT, smart city, and similar applications. However, current deep learning-based RPP methods lac…
MVQA-68K: A Multi-dimensional and Causally-annotated Dataset with Quality Interpretability for Video Assessment
Yanyun Pu, Kehan Li, Zeyi Huang +2
With the rapid advancement of video generation models such as Sora, video quality assessment (VQA) is becoming increasingly crucial for selecting high-quality videos from large-sca…
CCE: Confidence-Consistency Evaluation for Time Series Anomaly Detection
Zhijie Zhong, Zhiwen Yu, Yiu-ming Cheung +1
Time Series Anomaly Detection metrics serve as crucial tools for model evaluation. However, existing metrics suffer from several limitations: insufficient discriminative power, str…
PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detection
Zhijie Zhong, Zhiwen Yu, Yiyuan Yang +2
Time series anomaly detection is a pivotal task in data analysis, yet it poses the challenge of discerning normal and abnormal patterns in label-deficient scenarios. While prior st…