AI Paper Atlas

Research map / Time series / Foundation models for time series

Invariant Representation Learning for Source-Free Time Series Forecasting with LLM-Centric Proxy Denoising

Kangjia Yan, Chenxi Liu, Hao Miao, Xinle Wu, Yan Zhao, Chenjuan Guo, Bin Yang

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
add knowledge distillation from the denoised LLM to the target model (ablation)TimeID · ETTh1 -> ETTh2MSE / MAE: removal raises MSE 17.86% and MAE 18.34%Improved
add invariant disentangled feature learning (IDFL) (ablation)TimeID · ETTh1 -> TrafficMSE / MAE: removal raises MSE 20.13% and MAE 26.91%Improved
add proxy denoising of LLM predictions (ablation)TimeID · ETTh1 target datasetsMSE / MAEImproved
add LLM guidance (OFA backbone) (ablation)TimeID · ETTh1 target datasetsMSE / MAEImproved
add gradient-level invariant block (ablation)TimeID · ETTh1 target datasetsMSE / MAEImproved
increase target training data from 5% to 40% (ablation)TimeID · ETTh1 -> ETTh2 and ETTh1 -> ETTm2MSE / MAEImproved
use TimeID instead of Time-LLM and OFAsource-free forecasting · 18 tasks from ETTh1average MSE reduction vs Time-LLM: 4.98% MSE reduction vs Time-LLM, 4.39% vs OFAImproved
use TimeID instead of pretrained time series foundation models30% few-shot · ETTh1 -> TrafficMSE: 0.452 vs MOIRAI 0.368Hurt
use TimeID instead of foundation models30% few-shot · ETTh1 -> ETTh2 and WeatherMSE: 3.4% and 11.1% lower MSE than best foundation modelImproved

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