# RefineBridge: Generative Bridge Models Improve Financial Forecasting by Foundation Models

arXiv: https://arxiv.org/abs/2512.21572 · HTML: https://mlsanity.com/paper/2512.21572/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 32 references that are in the map.
- First posted on arXiv 25 Dec 2025.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modeling](https://mlsanity.com/paper/2106.01357/) (2021)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [VeRA: Vector-based Random Matrix Adaptation](https://mlsanity.com/paper/2310.11454/) (2023)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [Likelihood Training of Schr"odinger Bridge using Forward-Backward SDEs Theory](https://mlsanity.com/paper/2110.11291/) (2021)
- [Timer: Generative Pre-trained Transformers Are Large Time Series Models](https://mlsanity.com/paper/2402.02368/) (2024)
- [Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2310.08278/) (2023)
- [MASTER: Market-Guided Stock Transformer for Stock Price Forecasting](https://mlsanity.com/paper/2312.15235/) (2023)
- [Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis](https://mlsanity.com/paper/2312.03491/) (2023)
- [FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting](https://mlsanity.com/paper/2502.18834/) (2025)
- [FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation](https://mlsanity.com/paper/2507.08557/) (2025)
- [FrameBridge: Improving Image-to-Video Generation with Bridge Models](https://mlsanity.com/paper/2410.15371/) (2024)
- [Audio Super-Resolution with Latent Bridge Models](https://mlsanity.com/paper/2509.17609/) (2025)
- [RobustTrend: A Huber Loss with a Combined First and Second Order Difference Regularization for Time Series Trend Filtering](https://mlsanity.com/paper/1906.03751/) (2019)
- [Bridge-SR: Schr"odinger Bridge for Efficient SR](https://mlsanity.com/paper/2501.07897/) (2025)
- [ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling](https://mlsanity.com/paper/2510.08878/) (2025)
- [Beyond LoRA: Exploring Efficient Fine-Tuning Techniques for Time Series Foundational Models](https://mlsanity.com/paper/2409.11302/) (2024)
- [DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap](https://mlsanity.com/paper/2503.12131/) (2025)
- [Versatile Cardiovascular Signal Generation with a Unified Diffusion Transformer](https://mlsanity.com/paper/2505.22306/) (2025)

## Built on by (most cited first, 3 of 3)

- [Post-Training in Time Series Foundation Models: A Unifying Framework](https://mlsanity.com/paper/2607.20002/) (2026)
- [GuidedBridge: Training-freely Improving Bridge Models with Prior Guidance](https://mlsanity.com/paper/2606.03119/) (2026)
- [SR-Edit: Region-Aware Image Editing via Self-Refinement](https://mlsanity.com/paper/2609.02504/) (2026)

## Abstract (arXiv)

Financial time series forecasting is particularly challenging for transformer-based time series foundation models (TSFMs) due to non-stationarity, heavy-tailed distributions, and high-frequency noise present in data. Low-rank adaptation (LoRA) has become a popular parameter-efficient method for adapting pre-trained TSFMs to downstream data domains. However, it still underperforms in financial data, as it preserves the network architecture and training objective of TSFMs rather than complementing the foundation model. To further enhance TSFMs, we propose a novel refinement module, RefineBridge, built upon a tractable Schr"odinger Bridge (SB) generative framework. Given the forecasts of TSFM as generative prior and the observed ground truths as targets, RefineBridge learns context-conditioned stochastic transport maps to improve TSFM predictions, iteratively approaching the ground-truth target from even a low-quality prior. Simulations on multiple financial benchmarks demonstrate that RefineBridge consistently improves the performance of state-of-the-art TSFMs across different prediction horizons.