# Synthetic Stimuli, Real Gains: Rethinking VLM Fine-Tuning Through Fully Controlled Data Generation

arXiv: https://arxiv.org/abs/2511.11440 · HTML: https://mlsanity.com/paper/2511.11440/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 4 of its 45 references that are in the map.
- First posted on arXiv 14 Nov 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 4 of 4)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training](https://mlsanity.com/paper/2509.23661/) (2025)
- [Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation](https://mlsanity.com/paper/2506.23120/) (2025)
- [[De|Re]constructing VLMs' Reasoning in Counting](https://mlsanity.com/paper/2510.19555/) (2025)

## Built on by (most cited first, 2 of 2)

- [Learning Structured Robot Policies from Vision-Language Models via Synthetic Neuro-Symbolic Supervision](https://mlsanity.com/paper/2604.02812/) (2026)
- [WOVEN: Weaving Visual World Modeling into Multimodal LLMs](https://mlsanity.com/paper/2610.12417/) (2026)

## Abstract (arXiv)

Performance gains of Vision Language Models (VLMs) obtained by fine-tuning are generally based on ad hoc data collection and annotation of real-world scenes. Despite the improvements, this process is often prone to biases, errors, and distribution imbalance, resulting in overfitting and imbalanced performance. Although a few studies have explored synthetic data generation, they typically lack control over data distribution and annotation quality. In this work, we re-evaluate the potential of model fine-tuning by exploring a fully controlled data generation and annotation pipeline, obtaining bias-free data with balanced distribution and clean annotations. Using the spatial reasoning task of identifying the absolute position of an object as a use case, we fine-tune state-of-the-art VLMs and conduct exhaustive evaluations on both synthetic and real-world benchmarks, including transferability to real-world scenes. Our experiments reveal two key findings: 1) fine-tuning on balanced data yields uniform performance across the visual scene and mitigates common biases with as few as 130 samples; and 2) fine-tuning on synthetic stimuli improves performance by 13% on real-world data (COCO), outperforming models fine-tuned on the full COCO train set.