# VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization

arXiv: https://arxiv.org/abs/2505.10917 · HTML: https://mlsanity.com/paper/2505.10917/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 38 of its 48 references that are in the map.
- First posted on arXiv 16 May 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 30 of 38)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (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)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [A Diagram Is Worth A Dozen Images](https://mlsanity.com/paper/1603.07396/) (2016)
- [OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation](https://mlsanity.com/paper/2311.17911/) (2023)
- [Kimi-VL Technical Report](https://mlsanity.com/paper/2504.07491/) (2025)
- [LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models](https://mlsanity.com/paper/2407.12772/) (2024)
- [MetaMorph: Multimodal Understanding and Generation via Instruction Tuning](https://mlsanity.com/paper/2412.14164/) (2024)
- [MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI](https://mlsanity.com/paper/2404.16006/) (2024)
- [TinyLLaVA: A Framework of Small-scale Large Multimodal Models](https://mlsanity.com/paper/2402.14289/) (2024)
- [Multimodal Autoregressive Pre-training of Large Vision Encoders](https://mlsanity.com/paper/2411.14402/) (2024)

## Built on by (most cited first, 12 of 12)

- [From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents](https://mlsanity.com/paper/2506.18959/) (2025)
- [MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning](https://mlsanity.com/paper/2507.12062/) (2025)
- [Fine-Grained Zero-Shot Object Detection](https://mlsanity.com/paper/2507.10358/) (2025)
- [VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs](https://mlsanity.com/paper/2511.20272/) (2025)
- [Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition](https://mlsanity.com/paper/2606.00959/) (2026)
- [Rethinking the Text-Vision Reasoning Imbalance in MLLMs through the Lens of Training Recipes](https://mlsanity.com/paper/2510.22836/) (2025)
- [Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models](https://mlsanity.com/paper/2603.27375/) (2026)
- [Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models](https://mlsanity.com/paper/2605.30713/) (2026)
- [MIRROR: Aligning Semantic Relations from Language to Image via Gromov--Wasserstein](https://mlsanity.com/paper/2606.29462/) (2026)
- [UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm](https://mlsanity.com/paper/2609.27915/) (2026)
- [VIVAS: Vitalizing Visual Perception in VLM Pre-training via Vision-language Unified Autoregressive Supervision](https://mlsanity.com/paper/2609.27948/) (2026)
- [Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models](https://mlsanity.com/paper/2605.18160/) (2026)

## Abstract (arXiv)

Current multimodal large language models (MLLMs) face a critical challenge in modality alignment, often exhibiting a bias towards textual information at the expense of other modalities like vision. This paper conducts a systematic information-theoretic analysis of the widely used cross-entropy loss in MLLMs, uncovering its implicit alignment objective. Our theoretical investigation reveals that this implicit objective has inherent limitations, leading to a degradation of cross-modal alignment as text sequence length increases, thereby hindering effective multimodal information fusion. To overcome these drawbacks, we propose Vision-Text Alignment (VISTA), a novel approach guided by our theoretical insights. VISTA introduces an explicit alignment objective designed to maximize cross-modal mutual information, preventing the degradation of visual alignment. Notably, VISTA enhances the visual understanding capabilities of existing MLLMs without requiring any additional trainable modules or extra training data, making it both efficient and practical. Our method significantly outperforms baseline models across more than a dozen benchmark datasets, including VQAv2, MMStar, and MME, paving the way for new directions in MLLM modal alignment research.