AI Paper Atlas

Research map / Time series / Causal and generative time series

CombinationTS: A Modular Framework for Understanding Time-Series Forecasting Models

Xiaorui Wang, Fanda Fan, Chenxi Wang, Yuxuan Yang, Rui Tang, Kuoyu Gao, simiao pang, Yuanfeng Shang, Zhipeng Liu, Wanling Gao, Lei Wang, Jianfeng Zhan

ICML 2026 · Time series › Causal and generative time series · approach: Probabilistic and conformal 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
use parameter-free Identity encoder instead of Transformer encoder (ablation)modular forecasting pipeline with RevIN and linear decoder · ETTh1avg marginalized MSE: 0.5095 -> 0.4392Improved
use Identity encoder instead of Transformer encoder (ablation)modular forecasting pipeline · ETTm2avg marginalized MSE: 0.2909 -> 0.2621Improved
use Identity encoder instead of Transformer encoder (ablation)modular forecasting pipeline · Electricityavg marginalized MSE: 0.1776 -> 0.1888Hurt
use Identity encoder instead of Transformer, all datasets combined (ablation)modular forecasting pipeline · six datasets combinedMSE (Mann-Whitney U test): p<0.0001 vs Transformer; p=0.0115 vs MLPImproved
use structured tokenization (patch-wise or variate-wise) instead of point-wise embedding (ablation)modular forecasting pipeline · ETTh1avg marginalized MSE: 0.4367 -> 0.4277 (patch); 0.4285 (variate)Improved
use parameter-free Time-as-Feature reshape instead of learnable embeddings (ablation)modular forecasting pipeline · ETT datasetsmarginalized MSE: ETTh1 avg 0.4398 vs point-wise 0.4367No clear effect
add Cycle (learnable periodic) input transformation instead of RevIN-only baseline (ablation)point/variate-wise embedding models · ETTh1marginalized MSE: 0.3975 -> 0.3891Improved
add Cycle input transformation (ablation)point/variate-wise embedding models · Weathermarginalized MSE: 0.1882 -> 0.1917Hurt
add naive multi-scale downsampling instead of RevIN-only (ablation)point/variate-wise embedding models · ETTh2 and Weathermarginalized MSE: ETTh2 0.3013 -> 0.3071; Weather 0.1882 -> 0.1950Hurt
add naive multi-scale downsampling instead of RevIN-only (ablation)point/variate-wise embedding models · Electricitymarginalized MSE: 0.2061 -> 0.1952Improved
add trend-seasonal decomposition instead of RevIN-only (ablation)point/variate-wise embedding models · ETTh1marginalized MSE: 0.3975 -> 0.3947Mixed
replace attention with spectral (SimpleTM) encoder under variate-wise embedding (ablation)iTransformer · ETTm2avg marginalized MSE: 0.2870 -> 0.2697Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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