DualCast: A Dual-Path Language Model for Bimodal Financial Time-Series Forecasting
cs.LG, cs.AI
Submitted: 2026-09-18
Updated: 2026-09-18
Sources
- Chronos: Learning the Language of Time Series
- TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis
- Time Series Forecasting via Reasoning: A Slow-Thinking Approach with Reinforcement Fine-Tuned LLMs
- Eliciting Chain-of-Thought Reasoning for Time Series Analysis using Reinforcement Learning
- Qwen3 Technical Report
- LoRA: Low-Rank Adaptation of Large Language Models
- A decoder-only foundation model for time-series forecasting
- Unified Training of Universal Time Series Forecasting Transformers
- MOMENT: A Family of Open Time-series Foundation Models
- Timer: Generative Pre-trained Transformers Are Large Time Series Models
- Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts
- Sundial: A Family of Highly Capable Time Series Foundation Models
- From Knowing to Doing: A Memory-Controlled Benchmark for LLM Trading Agents on Stock Markets
- A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
- FinBERT: Financial Sentiment Analysis with Pre-trained Language Models
- BloombergGPT: A Large Language Model for Finance
- FinGPT: Open-Source Financial Large Language Models
- Achieving Time Series Reasoning Requires Rethinking Model Design, Tasks Formulation, and Evaluation
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks