The dynamic request patterns of machine learning (ML) inference workload...
We introduce a frustratingly simple, super efficient and surprisingly
ef...
Large language models (LLMs) have shown surprisingly good performance in...
Fine-tuning pre-trained models has been ubiquitously proven to be effect...
The rapid advances in automation technologies, such as artificial
intell...
Graph learning models are critical tools for researchers to explore
grap...
Graph contrastive learning has emerged as a powerful tool for unsupervis...
Maintaining a consistent persona is essential for building a human-like
...
Parameter-efficient tuning aims to distill knowledge for downstream task...
Unsupervised graph representation learning has emerged as a powerful too...
User purchasing prediction with multi-behavior information remains a
cha...
Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target
s...
Emphasis Selection is a newly proposed task which focuses on choosing wo...
Serverless computing, or Function-as-a-Service (FaaS), enables a new way...
While most existing segmentation methods usually combined the powerful
f...
Unstructured Persona-oriented Dialogue Systems (UPDS) has been demonstra...