# AdaCast: Conditional Parameter Generation for Adaptive Time Series Forecasting

arXiv: https://arxiv.org/abs/2610.12240 · HTML: https://mlsanity.com/paper/2610.12240/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 37 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Builds on (most cited first, 9 of 9)

- [GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation](https://mlsanity.com/paper/2410.10393/) (2024)
- [Chronos-2: From Univariate to Universal Forecasting](https://mlsanity.com/paper/2510.15821/) (2025)
- [TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster](https://mlsanity.com/paper/2503.07649/) (2025)
- [Toto 2.0: Time Series Forecasting Enters the Scaling Era](https://mlsanity.com/paper/2605.20119/) (2026)
- [Retrieval Augmented Time Series Forecasting](https://mlsanity.com/paper/2505.04163/) (2025)
- [Stationarity-Aware Retrieval-Augmented Time Series Forecasting](https://mlsanity.com/paper/2606.04135/) (2026)
- [Time Series Forecasting with Hypernetworks Generating Parameters in Advance](https://mlsanity.com/paper/2211.12034/) (2022)
- [Time Series Foundation Models as Strong Baselines in Transportation Forecasting: A Large-Scale Benchmark Analysis](https://mlsanity.com/paper/2602.24238/) (2026)
- [COPRA: Conditional Parameter Adaptation with Reinforcement Learning for Video Anomaly Detection](https://mlsanity.com/paper/2605.15325/) (2026)

## Abstract (arXiv)

Time-series foundation models (TSFMs) have achieved strong forecasting performance across domains. However, most adaptation methods remain static. Existing all-in-one methods learn a single set of dataset-level parameter updates and apply the same adapted model to every input. As a result, they cannot adapt the model parameters to the temporal patterns, seasonality and dynamics of each input time series. This limits their ability to produce forecasts that are tailored to heterogeneous inputs. To address this limitation, we propose AdaCast, a conditional parameter generation framework for time-series forecasting. AdaCast uses a generator to produce input-specific low-rank parameter updates for a frozen pretrained TSFM. These updates adapt the model to each input during both training and inference. Across six public benchmarks, AdaCast consistently outperforms static adaptation baseline in in-domain forecasting and improves zero-shot generalization to held-out datasets across domains. These results demonstrate that conditional parameter generation provides an effective approach for adaptive forecasting.