Pooling Helps, Learned Weighting Hurts In-Context: Decomposing Group Attention
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Sources
- The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting
- AverageTime: Enhance Long-Term Time Series Forecasting with Simple Averaging
- Do We Really Need Adaptive Global Spatial Attention for Traffic Forecasting?
- Universal Redundancies in Time Series Foundation Models
- Chronos-2: From Univariate to Universal Forecasting
- Unified Training of Universal Time Series Forecasting Transformers
- This Time is Different: An Observability Perspective on Time Series Foundation Models
- TiRex-2: Generalizing TiRex to Multivariate Data and Streaming
- RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks