# DV-SFT: Direct Vision Supervision for Fine-Grained Visual Understanding

arXiv: https://arxiv.org/abs/2605.26656 · HTML: https://mlsanity.com/paper/2605.26656/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 26 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)

## Builds on (most cited first, 18 of 18)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [PaddleOCR 3.0 Technical Report](https://mlsanity.com/paper/2507.05595/) (2025)
- [Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations](https://mlsanity.com/paper/2410.02762/) (2024)
- [Mitigating Hallucination in Visual Language Models with Visual Supervision](https://mlsanity.com/paper/2311.16479/) (2023)
- [DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies](https://mlsanity.com/paper/2503.14324/) (2025)
- [Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better](https://mlsanity.com/paper/2506.09040/) (2025)
- [Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models](https://mlsanity.com/paper/2505.17316/) (2025)
- [Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention](https://mlsanity.com/paper/2511.20032/) (2025)
- [EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding](https://mlsanity.com/paper/2603.18001/) (2026)

## Abstract (arXiv)

Multimodal large language models are typically trained end-to-end to predict ground-truth answers, yet supervision signals are applied exclusively to text tokens. Visual tokens, the core carriers of visual information, are optimized only implicitly as part of the context, leading to coarse-grained visual understanding. Prior works attempt to supervise visual inputs but inevitably rely on auxiliary components such as additional decoders or forward passes, because visual tokens lack readily interpretable labels. This limits their practical applicability. In this work, we propose Direct Vision Supervised Fine-Tuning (DV-SFT), which constructs explicit, token-level supervision for visual tokens and trains them through the same next-token prediction objective used for text. Specifically, we exploit the direct vision--text correspondence in OCR-related scenarios and automatically label each visual token with the word in its corresponding image patch. DV-SFT treats the MLLM as a black box, requiring no architectural modifications or additional forward passes. Extensive experiments demonstrate the superiority of direct vision supervision. DV-SFT consistently outperforms standard SFT across three in-domain and four out-of-domain benchmarks. Further analyses show that vision supervision effectively enhances fine-grained visual understanding and achieves higher multimodal alignment efficiency.