7 papers
FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer
Shenghe Zheng, Minyu Zhang, Tianhao Liu +1
With the growing availability of open-sourced adapters trained on the same diffusion backbone for diverse scenes and objects, combining these pretrained weights enables low-cost cu…
FREE-Merging: Fourier Transform for Efficient Model Merging
Shenghe Zheng, Hongzhi Wang
With the rapid growth of deep learning, there is an increasing availability of open-source models for various tasks. However, single fine-tuned models often fall short of meeting t…
Algorithmic Complexity Attacks on All Learned Cardinality Estimators: A Data-centric Approach
Yingze Li, Xianglong Liu, Dong Wang +4
Learned cardinality estimators show promise in query cardinality prediction, yet they universally exhibit fragility to training data drifts, posing risks for real-world deployment.…
Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging
Shenghe Zheng, Hongzhi Wang, Chenyu Huang +5
With more open-source models available for diverse tasks, model merging has gained attention by combining models into one, reducing training, storage, and inference costs. Current…
Brame: Hierarchical Data Management Framework for Cloud-Edge-Device Collaboration
Xianglong Liu, Hongzhi Wang, Yingze Li +3
In the realm of big data, cloud-edge-device collaboration is prevalent in industrial scenarios. However, a systematic exploration of the theory and methodologies related to data ma…
IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors
Shenghe Zheng, Hongzhi Wang, Xianglong Liu
Graph Neural Networks (GNNs) have shown great performance in various tasks, with the core idea of learning from data labels and aggregating messages within the neighborhood of node…