--- format: "aidr-story-markdown/v1" id: "edfff1af226cc0177e5e0c113482977f39c6b05827d66abc56e13a725985fa39" canonical_url: "https://aidr.today/edfff1af?lang=en" title: "DualCast: A Dual-Path Language Model for Bimodal Financial Time-Series Forecasting" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-10-01T04:00:00.000Z" category: "Research" topics: ["llm"] source_urls: ["https://arxiv.org/abs/2609.38197"] summary: "arXiv:2609.38197v1 Announce Type: new Abstract: Financial time-series forecasting must capture price dynamics across heterogeneous assets while incorporating news available at prediction time. We introduce DualCast, a dual-path framework that extends a frozen language model with a discrete financial vocabulary. Each log-return patch is represented by a learned summary token and three residual shape tokens, preserving local drift and volatility while allowing shape patterns to be shared across assets. To improve codebook utilization, we develop adaptive frequency-equalizing residual vector quantization, which rebalances overloaded codewords without compromising reconstruction accuracy. The fast path trains only the new financial-token embeddings and output heads on a frozen Qwen3-8B backbone. A toggleable LoRA adapter enables a slow path that conditions on the fast forecast and news available at the forecast origin to produce a revised prediction. The reviser is initialized by supervised fine-tuning and further optimized with a return-space group relative policy optimization objective that rewards improvements over the fast forecast. In zero-shot evaluations covering equities and en" --- # DualCast: A Dual\-Path Language Model for Bimodal Financial Time\-Series Forecasting > [Open the canonical story]() **Published:** 2026-10-01T04:00:00.000Z **Category:** Research **Topics:** llm ## Summary arXiv:2609\.38197v1 Announce Type: new Abstract: Financial time\-series forecasting must capture price dynamics across heterogeneous assets while incorporating news available at prediction time\. We introduce DualCast, a dual\-path framework that extends a frozen language model with a discrete financial vocabulary\. Each log\-return patch is represented by a learned summary token and three residual shape tokens, preserving local drift and volatility while allowing shape patterns to be shared across assets\. To improve codebook utilization, we develop adaptive frequency\-equalizing residual vector quantization, which rebalances overloaded codewords without compromising reconstruction accuracy\. The fast path trains only the new financial\-token embeddings and output heads on a frozen Qwen3\-8B backbone\. A toggleable LoRA adapter enables a slow path that conditions on the fast forecast and news available at the forecast origin to produce a revised prediction\. The reviser is initialized by supervised fine\-tuning and further optimized with a return\-space group relative policy optimization objective that rewards improvements over the fast forecast\. In zero\-shot evaluations covering equities and en ## Sources - [Story source]()