# Optimizing Vision-Language Interactions Through Decoder-Only Models

arXiv: https://arxiv.org/abs/2412.10758 · HTML: https://mlsanity.com/paper/2412.10758/

## Key facts

- No citing papers in the map yet (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 16 of its 18 references that are in the map.
- First posted on arXiv 14 Dec 2024.

## 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, 16 of 16)

- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [MoE-LLaVA: Mixture of Experts for Large Vision-Language Models](https://mlsanity.com/paper/2401.15947/) (2024)
- [Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning](https://mlsanity.com/paper/2405.10292/) (2024)
- [VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks](https://mlsanity.com/paper/2406.08394/) (2024)
- [Visual In-Context Learning for Large Vision-Language Models](https://mlsanity.com/paper/2402.11574/) (2024)
- [Unveiling Encoder-Free Vision-Language Models](https://mlsanity.com/paper/2406.11832/) (2024)
- [Enhancing Large Vision Language Models with Self-Training on Image Comprehension](https://mlsanity.com/paper/2405.19716/) (2024)
- [ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification](https://mlsanity.com/paper/2203.02225/) (2022)
- [Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models](https://mlsanity.com/paper/2410.19732/) (2024)
- [EventBERT: A Pre-Trained Model for Event Correlation Reasoning](https://mlsanity.com/paper/2110.06533/) (2021)
- [TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens](https://mlsanity.com/paper/2410.05261/) (2024)
- [Multimodal Event Transformer for Image-guided Story Ending Generation](https://mlsanity.com/paper/2301.11357/) (2023)
- [Style-Aware Contrastive Learning for Multi-Style Image Captioning](https://mlsanity.com/paper/2301.11367/) (2023)

## Abstract (arXiv)

Vision-Language Models (VLMs) have emerged as key enablers for multimodal tasks, but their reliance on separate visual encoders introduces challenges in efficiency, scalability, and modality alignment. To address these limitations, we propose MUDAIF (Multimodal Unified Decoder with Adaptive Input Fusion), a decoder-only vision-language model that seamlessly integrates visual and textual inputs through a novel Vision-Token Adapter (VTA) and adaptive co-attention mechanism. By eliminating the need for a visual encoder, MUDAIF achieves enhanced efficiency, flexibility, and cross-modal understanding. Trained on a large-scale dataset of 45M image-text pairs, MUDAIF consistently outperforms state-of-the-art methods across multiple benchmarks, including VQA, image captioning, and multimodal reasoning tasks. Extensive analyses and human evaluations demonstrate MUDAIF's robustness, generalization capabilities, and practical usability, establishing it as a new standard in encoder-free vision-language models.