Stock price prediction remains a complex and high-stakes task in financial analysis, traditionally addressed using statistical models or, more recently, language models. In this work, we introduce VISTA (Vision-Language Inference for Stock Time-series Analysis), a novel, training-free framework that leverages Vision-Language Models (VLMs) for multi-modal stock forecasting. VISTA prompts a VLM with both textual representations of historical stock prices and their corresponding line charts to predict future price values. By combining numerical and visual modalities in a zero-shot setting and using carefully designed chain-of-thought prompts, VISTA captures complementary patterns that unimodal approaches often miss. We benchmark VISTA against standard baselines, including ARIMA and text-only LLM-based prompting methods. Experimental results show that VISTA outperforms these baselines by up to 89.83%, demonstrating the effectiveness of multi-modal inference for stock time-series analysis and highlighting the potential of VLMs in financial forecasting tasks without requiring task-specific training.
@article{arxiv.2505.18570,
title = {VISTA: Vision-Language Inference for Training-Free Stock Time-Series Analysis},
author = {Tina Khezresmaeilzadeh and Parsa Razmara and Seyedarmin Azizi and Mohammad Erfan Sadeghi and Erfan Baghaei Potraghloo},
journal= {arXiv preprint arXiv:2505.18570},
year = {2026}
}
Comments
Accepted to the CVPR 2025 Workshop on Transformers for Vision (T4V): https://sites.google.com/view/t4v-cvpr25/accepted-papers