FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting

arXiv:2512.14253 · cs.LG · Submitted 2025-12-16 · Read on arXiv

cs.LG

Submitted: 2025-12-16

Updated: 2026-09-25

Code: https://github.com/amazon-science/unconditional-time-series-diffusion

Terminology

• Time Series Forecasting — 62× in this paper · explained in 3 episodes
• Probabilistic Forecasting — 29× in this paper · explained in 3 episodes
• Transformer — 27× in this paper · explained in 2 episodes
• Foundation Model — 25× in this paper · explained in 3 episodes
• Foundation Models — 23× in this paper · explained in 7 episodes
• Generalization — 15× in this paper · explained in 13 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Alignment — 7× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Benchmarking — 5× in this paper · explained in 3 episodes
• Diffusion Model — 5× in this paper · explained in 8 episodes
• Diffusion Models — 5× in this paper · explained in 6 episodes
• Mean Absolute Error — 5× in this paper
• Mean Squared Error — 3× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• Continuous Ranked Probability Score — 2× in this paper
• Decoupling — 2× in this paper · explained in 2 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Local Perception — 2× in this paper
• Normalized Mean Absolute Error — 2× in this paper
• Tokenization — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation Studies — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Commentary — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Hierarchical Classification — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Mixture of Experts — 1× in this paper · explained in 2 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Non-stationarity — 1× in this paper · explained in 2 episodes
• Normalizing Flow — 1× in this paper · explained in 3 episodes
• Normalizing Flows — 1× in this paper · explained in 4 episodes
• Ordinary Differential Equations (ODEs) — 1× in this paper · explained in 2 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Structured State-Space Duality — 1× in this paper
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
• GPT-4 Technical Report
• The UEA multivariate time series classification archive, 2018
• Monash Time Series Forecasting Archive
• VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline
• Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts
• Sundial: A Family of Highly Capable Time Series Foundation Models
• Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
• SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting
• Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances
• DeepSeek-V3 Technical Report
• DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables
• A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspective
• Instance Normalization: The Missing Ingredient for Fast Stylization
• An Encode-then-Decompose Approach to Unsupervised Time Series Anomaly Detection on Contaminated Training Data--Extended Version
• ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding
• WcDT: World-centric Diffusion Transformer for Traffic Scene Generation

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