AI Paper Atlas

Research map / Time series / Long-term forecasting

Dynamic Semantic Tokenization for Time Series via Elastic Sampling on Physics-aware Perception

Huaizhang Liao, Zhixiong Yang, Jingyuan Xia, Yuheng Sun, Yue Zhang, Shengxi Li, Yongxiang Liu

AAAI 2026 · Time series › Long-term forecasting · approach: Spatiotemporal forecasting models · 2 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 physics-aware sampling (PA) to the tokenizer (ablation)PATK · Epilepsyaccuracy: 79.13 -> 85.35Improved
add length adaptation re-weighting (LA) (ablation)PATK · Epilepsyaccuracy: 85.35 -> 91.27Improved
add token significance re-weighting (TS) (ablation)PATK · Epilepsyaccuracy: 91.27 -> 95.25Improved
add physics-aware loss (PAL) (ablation)PATK · Epilepsyaccuracy: 95.25 -> 95.75Improved
add physics-aware loss (PAL) (ablation)PATK · FD-Baccuracy: 83.55 -> 84.45Improved
add LA re-weighting over PA only (ablation)PATK · EMGaccuracy: 80.38 -> 93.35Improved
plug PATK tokens into OFAOFA · Epilepsyaccuracy: 74.13 -> 84.12Improved
plug PATK tokens into MoiraiMoirai · Epilepsyaccuracy: 74.53 -> 84.78Improved
plug PATK tokens into CALFCALF · Epilepsyaccuracy: 75.12 -> 78.34Improved
plug PATK tokens into OFA for forecastingOFA · ElectricityMSE: 0.2634 -> 0.2539Improved
use PATK tokenization versus SimMTM at long horizonSimMTM · ETTh1 horizon 720MSE: 0.4468 -> 0.4402Improved
use PATK on standard-length forecastingPATK · ETTh1 horizon 96MSE: 0.3792 vs 0.3715 (VisionTS)No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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