Raw-Routed Mixture of Adapters: A Causal Intervention for Routing Collapse in Time Series Foundation Models
cs.LG, stat.ML
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
- Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
- TRACE: Time SeRies PArameter EffiCient FinE-tuning
- AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting
- GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
- ST-MoE: Designing Stable and Transferable Sparse Expert Models
- ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization
- Routing-Free Mixture-of-Experts
- Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling
- On the Role of Reversible Instance Normalization
- The Myth of Expert Specialization in MoEs: Why Routing Reflects Geometry, Not Necessarily Domain Expertise
- IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning
- Mixtral of Experts
- Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
- A Survey on Mixture of Experts in Large Language Models
- Representation Learning with Contrastive Predictive Coding
- Instance Normalization: The Missing Ingredient for Fast Stylization
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks