While methods for comparing two learning algorithms on a single data set have been
scrutinized for quite some time already, the issue of statistical tests for comparisons of more …

The surprising ability of Large Language Models (LLMs) to perform well on complex
reasoning with only few-shot chain-of-thought prompts is believed to emerge only in very …

Prompting a pretrained language model with natural language patterns has been proved
effective for natural language understanding (NLU). However, our preliminary study reveals …

Abstract Model-agnostic meta learning (MAML) is currently one of the dominating
approaches for few-shot meta-learning. Albeit its effectiveness, the optimization of MAML …

Source-free unsupervised domain adaptation (SFUDA) aims to obtain high performance in
the unlabeled target domain using the pre-trained source model, not the source data …

Guided sampling is a vital approach for applying diffusion models in real-world tasks that
embeds human-defined guidance during the sampling procedure. This paper considers a …

Globalization processes and market deregulation policies are rapidly changing the
competitive environments of many economic sectors. The appearance of new competitors …

Code generation models based on the pre-training and fine-tuning paradigm have been
increasingly attempted by both academia and industry, resulting in well-known industrial …

Neural networks have been successfully applied in applications with a large amount of
labeled data. However, the task of rapid generalization on new concepts with small training …

This paper critiques popular modes of participation in design practice and machine learning.
It examines three existing kinds of participation in design practice and machine learning …