CoGenCast: A Coupled Autoregressive-Flow Generative Framework for Time Series Forecasting

TL;DR

CoGenCast introduces a hybrid generative framework combining pre-trained language models with flow-matching for improved time series forecasting, effectively modeling both semantic context and stochastic dynamics.

Contribution

It reconfigures pre-trained LLMs into a bidirectional encoder-decoder for forecasting and integrates flow-matching to model temporal stochasticity, supporting multimodal and cross-domain tasks.

Findings

Outperforms previous baselines on multiple benchmarks.

Supports multimodal and cross-domain forecasting.

Effectively models both semantic context and stochastic dynamics.

Abstract

Time series forecasting can be viewed as a generative problem that requires both semantic understanding over contextual conditions and stochastic modeling of continuous temporal dynamics. Existing approaches typically rely on either autoregressive large language models (LLMs) for semantic context modeling or diffusion-like models for continuous probabilistic generation. However, neither method alone can adequately model both aspects simultaneously. In this work, we propose CoGenCast, a hybrid generative framework that couples pre-trained LLMs with flow-matching mechanism for effective time series forecasting. Specifically, we reconfigure pre-trained decoder-only LLMs into a native forecasting encoder-decoder backbone by modifying only the attention topology, enabling bidirectional context encoding and causal representation generation. Building on this, a flow-matching mechanism is further integrated to model temporal evolution, capturing continuous stochastic dynamics conditioned on the autoregressively generated representation. Notably, CoGenCast naturally supports multimodal forecasting and cross-domain unified training. Extensive experiments on multiple benchmarks show that CoGenCast consistently outperforms previous compared baselines. Code is available at https://github.com/liuyaguo/_CoGenCast.