AI Paper Atlas

Research map / Benchmarks / Weather Avg

Weather Avg leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Weather Avg. Best MSE: 0.227 (TimePerceiver, NeurIPS 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.

Weather Avg · MSE

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

#MSE ↓MethodPaperTopic
10.227TimePerceiverTimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting
NeurIPS 2025 · Table 1
Foundation models for time series
20.235U-MixerU-Mixer: An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting
AAAI 2024 · Table 1
Long-term forecasting
30.239TARFVAETARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE
NeurIPS 2025 · Table 1
Long-term forecasting
40.242TimeKANTimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting
ICLR 2025 · Main results table
Long-term forecasting
50.243Sequence Complementor
iTransformer
Sequence Complementor: Complementing Transformers for Time Series Forecasting with Learnable Sequences
AAAI 2025 · Table 1
Long-term forecasting
60.244FilterTSFilterTS: Comprehensive Frequency Filtering for Multivariate Time Series Forecasting
AAAI 2025 · Table 1
Long-term forecasting
70.245SOatten(V)
iTransformer
Revisiting Attention for Multivariate Time Series Forecasting
AAAI 2025 · Table: Multivariate forecastin
Long-term forecasting
80.25TimeCMA
GPT-2
TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment
AAAI 2025 · Table 1
Foundation models for time series
90.253iTransformer + PS
iTransformer
Patch-wise Structural Loss for Time Series Forecasting
ICML 2025 · Table 1
Long-term forecasting
100.261VarDrop
iTransformer
VarDrop: Enhancing Training Efficiency by Reducing Variate Redundancy in Periodic Time Series Forecasting
AAAI 2025 · Table 1
Long-term forecasting

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