2 citations · 2 across the 5 of their papers we have counts for
6 papers
Dynamics as Code: On Model Compression via Dynamic System
Fan Gao, Wei Su, Juntong Fan +4
The escalating size of pretrained neural networks has rendered model compression a prerequisite for deployment under stringent memory and compute constraints. With the irrational w…
TNLearn: An Open Source Python Package for Task-based Neurons
Meng Wang, Tieyun Li, Juntong Fan +5
The brain does not rely on a single type of neuron to perform all kinds of tasks; instead, it designs different neurons for different tasks. The concept of task-based neurons repre…
Self-Improving is Often Sudden: Enlightenment-style Finetuning for Large-Scale Models
Jing-Xiao Liao, Tianwei Zhang, Yu-Hao Jiang +3
The pursuit of autonomously self-improving models has attracted growing interest in the era of large-scale foundation models. Drawing inspiration from the concept of "enlightenment…
Compress Any Segment Anything Model (SAM)
Juntong Fan, Zhiwei Hao, Jianqiang Shen +4
Due to the excellent performance in yielding high-quality, zero-shot segmentation, Segment Anything Model (SAM) and its variants have been widely applied in diverse scenarios such…
NeuronSeek: On Stability and Expressivity of Task-driven Neurons
Hanyu Pei, Jing-Xiao Liao, Qibin Zhao +4
Drawing inspiration from our human brain that designs different neurons for different tasks, recent advances in deep learning have explored modifying a network's neurons to develop…
Enhancing the Performance of Neural Networks Through Causal Discovery and Integration of Domain Knowledge
Xiaoge Zhang, Xiao-Lin Wang, Fenglei Fan +2
In this paper, we develop a generic methodology to encode hierarchical causality structure among observed variables into a neural network in order to improve its predictive perform…