AI Paper Atlas

Research map / Benchmarks / ETTh1 Avg

ETTh1 Avg leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ETTh1 Avg. Best MSE: 0.379 (WPMixer, AAAI 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

ETTh1 Avg · MSE

12 papers, each with its best reported number for its own method; lower is better.

#MSE ↓MethodPaperTopic
10.379WPMixerWPMixer: Efficient Multi-Resolution Mixing for Long-Term Time Series Forecasting
AAAI 2025 · Table: Multivariate long-term
Long-term forecasting
20.41TimePerceiverTimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting
NeurIPS 2025 · Table 1
Foundation models for time series
30.411AffirmAffirm: Interactive Mamba with Adaptive Fourier Filters for Long-term Time Series Forecasting
AAAI 2025 · Table 2
Long-term forecasting
40.417TimeKANTimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting
ICLR 2025 · Main results table
Long-term forecasting
50.423TimeCMA
GPT-2
TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment
AAAI 2025 · Table 1
Foundation models for time series
60.423Implicit frequency evolutionAttractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective
NeurIPS 2024 · Table 4
Long-term forecasting
70.427TARFVAETARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE
NeurIPS 2025 · Table 1
Long-term forecasting
80.429Sequence Complementor
PatchTST
Sequence Complementor: Complementing Transformers for Time Series Forecasting with Learnable Sequences
AAAI 2025 · Table 1
Long-term forecasting
90.433DistDF with Bures-Wasserstein
TimeBridge
DistDF: Time-series Forecasting Needs Joint-distribution Wasserstein Alignment
ICLR 2026 · Table 3
Causal and generative time series
100.433FilterTSFilterTS: Comprehensive Frequency Filtering for Multivariate Time Series Forecasting
AAAI 2025 · Table 1
Long-term forecasting
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.