LLMFew, a framework that fine-tunes GPT-2 with LoRA after a convolutional patch encoder, substantially improves few-shot multivariate time series classification accuracy on 10 benchmark datasets.
World Wide Web 23(5), 2653–2669 (2020)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Large Language Models are Few-shot Multivariate Time Series Classifiers
LLMFew, a framework that fine-tunes GPT-2 with LoRA after a convolutional patch encoder, substantially improves few-shot multivariate time series classification accuracy on 10 benchmark datasets.