Does Scale Stealthily Hijack Attention? PMDformer’s Simple Subtraction Fix for Long-Term Forecasting

The paper identifies scale differences between patches as a hidden source of attention distortion in long‑term time‑series forecasting, introduces PMDformer with Patch Mean Decoupling, Neighbor Variable Attention, and Trend Recovery Attention, and demonstrates state‑of‑the‑art accuracy and efficiency across eight benchmark datasets.

Attention MechanismICLR2026Long-term Time Series Forecasting

0 likes · 8 min read

Does Scale Stealthily Hijack Attention? PMDformer’s Simple Subtraction Fix for Long-Term Forecasting

Bighead's Algorithm Notes

Sep 27, 2025 · Artificial Intelligence

Weekly Time-Series Paper Digest (Sep 20‑26, 2025)

This digest summarizes three recent arXiv papers that propose novel diffusion‑based generation, a channel‑independent convolution for multivariate forecasting, and a style‑guided diffusion framework, each demonstrating improved realism, coherence, and diversity of synthetic time‑series data through extensive experiments.

DS-DiffusionDiffusion ModelsIConv

0 likes · 8 min read

Weekly Time-Series Paper Digest (Sep 20‑26, 2025)

Model Perspective

Aug 24, 2022 · Fundamentals

How the GM(1,N) Grey Model Predicts Multi‑Variable Systems

The GM(1,N) prediction model extends the classic GM(1,1) approach to multiple indicator variables by applying accumulated generating operations, forming a first‑order differential equation, converting it to a discrete model, and using least‑squares estimation to derive prediction values for each variable.

Multivariate ForecastingPredictionTime Series

0 likes · 2 min read

How the GM(1,N) Grey Model Predicts Multi‑Variable Systems