HALO: Enhancing Time Series Generation via Hyperspherical Latents and Masked AutoregRessive Modeling
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-29
Code: https://github.com/decisionintelligence/TimeMAR
Sources
- GPT-4 Technical Report
- Hyperspherical Variational Auto-Encoders
- TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation
- Auto-Encoding Variational Bayes
- Vector Quantized Time Series Generation with a Bidirectional Prior Model
- Sequence Level Training with Recurrent Neural Networks
- FaultDiffusion: Few-Shot Fault Time Series Generation with Diffusion Model
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