Time-LLM reprograms frozen LLMs for time series forecasting via text prototypes and Prompt-as-Prefix, outperforming specialized models in standard, few-shot, and zero-shot settings.
17 A Belief States in Sequence Modeling Recent work has introduced variants of sequence modeling architectures based on the principle of learning belief states, i.e., BST and JTP
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 3roles
background 1polarities
background 1representative citing papers
Adding a next-latent prediction loss to next-token training makes transformer hidden states more predictive of future tokens and improves planning/reasoning on small benchmarks.
A survey that proposes a taxonomy for universal time-series representation learning and reviews existing deep learning studies along with experimental setups.
citing papers explorer
-
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
Time-LLM reprograms frozen LLMs for time series forecasting via text prototypes and Prompt-as-Prefix, outperforming specialized models in standard, few-shot, and zero-shot settings.
-
Next-Latent Prediction Transformers Learn Compact World Models
Adding a next-latent prediction loss to next-token training makes transformer hidden states more predictive of future tokens and improves planning/reasoning on small benchmarks.
-
Universal Time-Series Representation Learning: A Survey
A survey that proposes a taxonomy for universal time-series representation learning and reviews existing deep learning studies along with experimental setups.