AI Paper Atlas

Research map / Time series / Foundation models for time series

Byte Pair Encoding for Efficient Time Series Forecasting

Leon Götz, Marcel Kollovieh, Stephan Günnemann, Leo Schwinn

ICML 2026 · Time series › Foundation models for time series · approach: LLM-based time series forecasting · 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
replace sample-wise tokens with motif-based tokenizationChronos (T5) · 7 zero-shot datasetsMSE / speedup: 40% MSE, 2314% efficiency on averageImproved
add conditional decoding to motif tokenization (ablation)motif-based tokenizer · 7 zero-shot datasetsMSE: 39.8% -> 48.0% MSE improvement; 23.14x -> 28.22x accelerationImproved
add conditional decoding (ablation)motif tokenizer, high compression, small model · ETTm1MSE: -44.3% MSEImproved
replace fixed-length patches with motif tokenizationpatch-based Chronos (len 4 and 8) · 7 zero-shot datasetsMSE: 12.7% average gain with cdMixed
use higher compression tokenizer (fewer bins, larger quantization error) (ablation)motif tokenizer · 7 datasets x 5 model sizesMSE: 25 of 35 settings bestImproved
vary minimum motif occurrence p_min (ablation)motif tokenizer, small models · Electricity and TrafficMSEMixed
increase tokenizer training set from 1k to 1M series (ablation)motif tokenizer · 5 datasets avgMSE: 0.569 -> 0.533Improved
use longer motifs for generation (ablation)motif tokenizer medium, small model · 5 datasetstoken-wise MSE correlation: rho -0.26 on ETTh1Improved
use motif tokens instead of per-sample tokensChronos · Traffic zero-shotMSE: 2.717 -> 0.574Improved

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