UniTok tokenizes time series for an off-the-shelf LLM foundation model that unifies forecasting, generation, and classification through next-token prediction and training-free inference.
hub
Timevae: A variational auto-encoder for multivariate time series generation
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 13roles
baseline 1polarities
baseline 1representative citing papers
SRT decomposes low-resolution time series into trend and seasonal components, aligns them via implicit neural representations, and uses cross-resolution attention within a disentangled rectified flow to generate high-resolution outputs, with a scaled SRT-large variant for zero-shot use.
Proves SLiCEs are universal time-series generators approximating path laws in W_∞ and proposes G-SLiCEs for path-space flow matching with benefits on irregular grids.
PrismFlow augments flow matching with residual dynamical experts and a winner-take-all objective to reduce spectral distortion and improve mode coverage in time-series generation.
GenTS is a modular benchmark library providing unified data pipelines, generative models, and evaluation metrics for time series synthesis, forecasting, and imputation, with open-source code and initial benchmarking experiments.
SDFlow learns a global transport map via similarity-driven flow matching in VQ latent space, using low-rank manifold decomposition and a categorical posterior to handle discreteness, yielding SOTA long-horizon performance and inference speedups.
GCGNet uses a variational generator, graph structure aligner, and graph refiner to jointly capture temporal and channel correlations in time series forecasting with exogenous variables, outperforming baselines on 12 real-world datasets.
CAPS provides an iterative differentially private synthesis method that outperforms one-shot baselines on authentic educational real-world data.
E4GEN is an explainable diffusion model using E-Activator, E-Predictor, and E-Control for extreme-event-aware time-series generation evaluated on six datasets.
MOSAIC structures LLM-based model selection via memory-grounded blueprints and failure-aware RL, reporting gains in performance and traceability on financial time-series tasks over AutoML and agent baselines.
AutoReproduce is a multi-agent system using paper lineage to autonomously reproduce AI experiment code, with a new benchmark showing improvements over baselines in fidelity and execution.
MSDformer introduces a multi-scale discrete transformer that tokenizes time series at multiple scales and models them autoregressively in discrete space, claiming superior performance over prior DTM methods with rate-distortion theoretical support.
TriHead-GAN is a GAN framework whose triple-head discriminator supervises distributional authenticity, cross-variable dependency via regression, and temporal smoothness via adjacent-difference prediction for carbon emission time series.
citing papers explorer
-
Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models
UniTok tokenizes time series for an off-the-shelf LLM foundation model that unifies forecasting, generation, and classification through next-token prediction and training-free inference.
-
SRT: Super-Resolution for Time Series via Disentangled Rectified Flow
SRT decomposes low-resolution time series into trend and seasonal components, aligns them via implicit neural representations, and uses cross-resolution attention within a disentangled rectified flow to generate high-resolution outputs, with a scaled SRT-large variant for zero-shot use.
-
Universal Time Series Generation with Neural Controlled Differential Equations
Proves SLiCEs are universal time-series generators approximating path laws in W_∞ and proposes G-SLiCEs for path-space flow matching with benefits on irregular grids.
-
PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
PrismFlow augments flow matching with residual dynamical experts and a winner-take-all objective to reduce spectral distortion and improve mode coverage in time-series generation.
-
GenTS: A Comprehensive Benchmark Library for Generative Time Series Models
GenTS is a modular benchmark library providing unified data pipelines, generative models, and evaluation metrics for time series synthesis, forecasting, and imputation, with open-source code and initial benchmarking experiments.
-
SDFlow: Similarity-Driven Flow Matching for Time Series Generation
SDFlow learns a global transport map via similarity-driven flow matching in VQ latent space, using low-rank manifold decomposition and a categorical posterior to handle discreteness, yielding SOTA long-horizon performance and inference speedups.
-
GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variables
GCGNet uses a variational generator, graph structure aligner, and graph refiner to jointly capture temporal and channel correlations in time series forecasting with exogenous variables, outperforming baselines on 12 real-world datasets.
-
Cyclic Adaptive Private Synthesis for Sharing Real-World Data in Education
CAPS provides an iterative differentially private synthesis method that outperforms one-shot baselines on authentic educational real-world data.
-
E4GEN: Event-level Explainable Extreme-Enhanced Time-series Generation
E4GEN is an explainable diffusion model using E-Activator, E-Predictor, and E-Control for extreme-event-aware time-series generation evaluated on six datasets.
-
MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition
MOSAIC structures LLM-based model selection via memory-grounded blueprints and failure-aware RL, reporting gains in performance and traceability on financial time-series tasks over AutoML and agent baselines.
-
TriHead-GAN: A Generative Adversarial Network with Triple-Head Discriminator for Carbon Emission Time Series Generation
TriHead-GAN is a GAN framework whose triple-head discriminator supervises distributional authenticity, cross-variable dependency via regression, and temporal smoothness via adjacent-difference prediction for carbon emission time series.