Timer-S1 is a released 8.3B-parameter MoE time series model that achieves state-of-the-art MASE and CRPS scores on GIFT-Eval using serial scaling and Serial-Token Prediction.
The language instinct: How the mind creates language
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2verdicts
UNVERDICTED 2representative citing papers
LMNet connects stripped LLMs as nodes with trainable seq2seq edges for dense vector exchange, supporting supervision-efficient learning through differentiable communication.
citing papers explorer
-
Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling
Timer-S1 is a released 8.3B-parameter MoE time series model that achieves state-of-the-art MASE and CRPS scores on GIFT-Eval using serial scaling and Serial-Token Prediction.
-
Language Model Networks: Supervision-Efficient Learning through Dense Communication
LMNet connects stripped LLMs as nodes with trainable seq2seq edges for dense vector exchange, supporting supervision-efficient learning through differentiable communication.