AI Paper Atlas

Research map / Time series / Foundation models for time series

StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars

Weijian Li, Hong-Yu Chen, Nabeel Rehemtulla, Ved G. Shah, Dongho Kim, Dennis Wu, Qinjie Lin, Adam A. Miller, Han Liu

ICML 2026 · Time series › Foundation models for time series · approach: Time series foundation models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Chronos-Bolt embeddings with multi-class isolation forestOOD detection · StarEmbed OODOOD purity top 10%: 0.259 -> 0.519 vs hand-craftedImproved
swap isolation forest for Local Outlier Factor (ablation)Chronos OOD detection · StarEmbed OOD top 10%OOD purity: 0.149 -> 0.992Improved
fine-tune Chronos with classification head instead of forecasting objective (ablation)Chronos-tiny · StarEmbed classification (MLP)macro F1: 0.627 -> 0.659Improved
fine-tune Chronos with forecasting objective (ablation)Chronos-tiny · StarEmbed classification (MLP)macro F1: 0.643 -> 0.627Hurt
use LoRA instead of full fine-tuning with linear head (ablation)Chronos · StarEmbed classificationmacro F1: 0.661 -> 0.622Hurt
use LoRA instead of full fine-tuning with MLP head (ablation)Chronos-tiny · StarEmbed classificationmacro F1: 0.659 -> 0.661No clear effect
tune LayerNorm only instead of LoRA with MLP head (ablation)Chronos-tiny · StarEmbed classificationmacro F1: 0.661 -> 0.648Hurt
replace patch-index RoPE with true timestamps (ablation)Moirai · synthetic sinusoidsR2: 0.016 -> 0.188Improved
append time gaps as covariate instead of RoPE timestamps (ablation)Moirai · synthetic sinusoidsR2: 0.188 -> 0.044Hurt
scale Chronos from Tiny to Large (ablation)Chronos · StarEmbed k-NNmacro F1: 0.672 -> 0.646No clear effect
scale Moirai from Small to Large (ablation)Moirai · StarEmbed k-NNmacro F1: 0.554 -> 0.612Improved
full fine-tune Mantis models (ablation)MantisV2 · StarEmbed classification (MLP)macro F1: 0.570 -> 0.638Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy