# TailDART: Compute-Efficient Foundation Models for Financial Time-Series Forecasting

DevFeed: [TailDART: Compute-Efficient Foundation Models for Financial Time-Series Forecasting](<https://devfeed.tech/articles/taildart-compute-efficient-foundation-models-for-financial-time-series-forecasting-124631.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09176>)

Author: Chiang Qin Zhi, Ranjan Satapathy, Erik Cambria, Joyjit Chattoraj

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Time Series](<https://devfeed.tech/topics/time-series.md>), [Finance](<https://devfeed.tech/topics/finance.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>)

Tags: [acceleration](<https://devfeed.tech/tags/acceleration.md>), [attention](<https://devfeed.tech/tags/attention.md>), [autoregressive](<https://devfeed.tech/tags/autoregressive.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [compute](<https://devfeed.tech/tags/compute.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ce](<https://devfeed.tech/tags/cs-ce.md>), [decoding](<https://devfeed.tech/tags/decoding.md>), [error](<https://devfeed.tech/tags/error.md>), [finance](<https://devfeed.tech/tags/finance.md>), [financial](<https://devfeed.tech/tags/financial.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [grouped-query-attention](<https://devfeed.tech/tags/grouped-query-attention.md>), [inference](<https://devfeed.tech/tags/inference.md>), [key-value-cache](<https://devfeed.tech/tags/key-value-cache.md>), [latency](<https://devfeed.tech/tags/latency.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [time-series](<https://devfeed.tech/tags/time-series.md>), [time-series-forecasting](<https://devfeed.tech/tags/time-series-forecasting.md>)

## AI overview

TailDART is a 2.68-million-parameter model for financial time-series forecasting, designed to address low signal-to-noise ratios, non-stationarity, and the latency costs of autoregressive decoding. It uses grouped-query attention in a lightweight backbone to reduce key-value cache memory bandwidth overhead; the abstract reports inference acceleration of up to 48.1% over prevailing state-of-the-art time-series foundation models. Across multi-asset benchmarks at varying temporal resolutions, TailDART reportedly matches the predictive fidelity of substantially larger baselines and shows greater error resilience in high-volatility regimes. These findings are reported in the abstract; benchmark details are not included in the supplied text.

## Source excerpt

arXiv:2611.09176v1 Announce Type: new Abstract: Although time-series foundation models (TSFMs) achieve strong zero-shot transferability across high-information-density physical systems, applying overparameterized TSFMs to quantitative finance is fundamentally constrained by low signal-to-noise ratios, non-stationarity, and prohibitive autoregressive decoding latency. To reconcile representation learning with institutional operational constraints, this study presents TailDART, a dense 2.68 million-parameter foundation model engineered for financial time-series forecasting. By integrating grouped-query attention into a lightweight backbone, the architecture drastically reduces Key-Value cache memory bandwidth overhead, achieving major inference acceleration (up to 48.1%) over prevailing state-of-the-art TSFMs to enable low-latency, high-throughput streaming execution. Furthermore, multi-asset benchmarks across varying temporal resolutions show that a compact model can remain competitive for market forecasting: TailDART matches the predictive fidelity of substantially larger baselines while demonstrating superior error resilience in high-volatility regimes.