# Perceiving Beyond Language Priors: Enhancing Visual Comprehension and Attention in Multimodal Models

arXiv: https://arxiv.org/abs/2505.05626 · HTML: https://mlsanity.com/paper/2505.05626/

## Key facts

- Cited by 4 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 21 of its 22 references that are in the map.
- First posted on arXiv 8 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, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [MM-LLMs: Recent Advances in MultiModal Large Language Models](https://mlsanity.com/paper/2401.13601/) (2024)
- [AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One](https://mlsanity.com/paper/2312.06709/) (2023)
- [Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models](https://mlsanity.com/paper/2411.04996/) (2024)
- [Vision language models are blind: Failing to translate detailed visual features into words](https://mlsanity.com/paper/2407.06581/) (2024)
- [Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders](https://mlsanity.com/paper/2408.15998/) (2024)
- [LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models](https://mlsanity.com/paper/2312.02949/) (2023)
- [Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models](https://mlsanity.com/paper/2406.14852/) (2024)
- [Multimodal Autoregressive Pre-training of Large Vision Encoders](https://mlsanity.com/paper/2411.14402/) (2024)
- [Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models](https://mlsanity.com/paper/2404.07973/) (2024)
- [An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models](https://mlsanity.com/paper/2411.06048/) (2024)
- [Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning](https://mlsanity.com/paper/2410.16162/) (2024)
- [From colouring-in to pointillism: revisiting semantic segmentation supervision](https://mlsanity.com/paper/2210.14142/) (2022)

## Built on by (most cited first, 4 of 4)

- [ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps](https://mlsanity.com/paper/2505.18675/) (2025)
- [From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs](https://mlsanity.com/paper/2512.19683/) (2025)
- [VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning](https://mlsanity.com/paper/2509.25151/) (2025)
- [Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning](https://mlsanity.com/paper/2602.14518/) (2026)

## Abstract (arXiv)

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first provides insights into how MLLMs internally build visual understanding of image regions and then introduces techniques to amplify this capability. Specifically, we explore techniques designed both to deepen the model's understanding of visual content and to ensure that these visual insights actively guide language generation. We demonstrate the superior multimodal understanding of our resultant model through a detailed upstream analysis quantifying its ability to predict visually-dependent tokens as well as 10 pt boost on visually challenging tasks.