The paper investigates when auxiliary context can genuinely improve multi‑modal time series forecasting. It identifies two necessary dataset‑level conditions: the target must not be dominated by a last‑value shortcut (low autocorrelation) and the context must provide additional information beyond history (non‑zero conditional mutual information). Experiments on a large mixture‑of‑experts model and several fusion mechanisms show that only when both conditions hold does context routing yield a substantial reduction in mean‑squared error; otherwise its contribution collapses to a capacity floor.
arXiv:2508. 09904v3 Announce Type: replace-cross Abstract: Real-world forecasting requires models to integrate not only historical data but also relevant contextual information provided in textual form.
arXiv:2603. 12451v4 Announce Type: replace Abstract: Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to surpass traditional statistical methods.
arXiv:2606. 08365v1 Announce Type: cross Abstract: Sparse autoencoder (SAE) features are increasingly used to steer language models, but feature steering is rarely clean: the same intervention can behave inconsistently across contexts and perturb unrelated features.
arXiv:2609. 20193v1 Announce Type: new Abstract: Retrieval plug-ins supply a deep forecaster with information its lookback window cannot carry.
arXiv:2609.15087v1 Announce Type: cross Abstract: Most time series forecasting benchmarks remain numerical-centric and provide limited support for evaluating contextual information that shapes real-w...
arXiv:2608. 10433v2 Announce Type: replace Abstract: Temporal reports are increasingly emitted alongside numerical forecasts and are often interpreted as statements about the computation producing those forecasts.
arXiv:2609.24677v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to make predictions from numerical time-series histories and textual events. Yet accuracy alone cann...
arXiv:2609.39445v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) commonly adapt to new data by attaching a single trainable head to a frozen backbone, a one-size-fits-all setup...
arXiv:2604. 26866v2 Announce Type: replace-cross Abstract: Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction.
arXiv:2606. 25092v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models route each token to a few of many experts, inviting the hypothesis that experts form functional modules tied to capabilities or languages.
arXiv:2608. 11623v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have spurred cross-modal solutions for time-series forecasting.
arXiv:2608. 16098v1 Announce Type: cross Abstract: Multivariate time-series forecasting faces a structural dilemma: sharing one temporal predictor across variables is parameter-efficient but forces heterogeneous variables through an identical history-to-future map, whereas learning an independent predictor per variable restores flexibility at a cost that grows with the product of variable count, context length, and horizon.