Several post-training quantization methods have been applied to large language models
(LLMs), and have been shown to perform well down to 8-bits. We find that these methods …

Data-free meta-learning (DFML) aims to enable efficient learning of new tasks by meta-
learning from a collection of pre-trained models without access to the training data. Existing …

The goal of data-free meta-learning is to learn useful prior knowledge from a collection of
pre-trained models without accessing their training data. However, existing works only solve …

Model inversion, which aims to reconstruct the original training data from pre-trained
discriminative models, is especially useful when the original training data is unavailable due …

Deploying models across diverse devices demands tradeoffs among multiple objectives due
to different resource constraints. Arguably, due to the small model trap problem in multi …

Conventional multi-label recognition methods often focus on label confidence, frequently
overlooking the pivotal role of partial order relations consistent with human preference. To …

In many image classification applications, the number of labeled training images is limited,
which leads to model overfitting. To mitigate the lack of training data, deep generative …

Neural Architecture Search (NAS) aims to automatically find effective architectures within a
predefined search space. However, the search space is often extremely large. As a result …

Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple
pre-trained models without requiring their original training data. Existing inversion-based …

针对神经网络结构搜索方法(NAS) 在搜索最优结构时存在性能评估效率偏低,
以及由于模型泛化性能力不足导致液压泵故障诊断精度过低等问题, 提出一种改进的Data-free …