From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models
Quick Answer
This paper shows that This survey presents a systematic examination of Multimodal Large Language Models (MLLMs), emphasizing a unified vision-language perception framework.
Quick Take
This survey presents a systematic examination of Multimodal Large Language Models (MLLMs), emphasizing a unified vision-language perception framework. It introduces a five-stage taxonomy of MLLM perception evolution and highlights open challenges and future research directions to advance toward artificial general intelligence (AGI).
Key Points
- Formalizes MLLM perception as a unified capability akin to human perception.
- Introduces a five-stage taxonomy tracing MLLM perception evolution.
- Surveys key methods and milestones in vision-language integration.
- Identifies open challenges in achieving unified multimodal intelligence.
- Aims to provide a roadmap for advancing artificial general intelligence.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 26196v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have recently made remarkable progress in unifying vision-language understanding and reasoning, especially following the introduction of models such as OpenAI's O-series and DeepSeek's R-series, which have driven a paradigm shift toward perception-centric intelligence.
However, there remains a lack of systematic surveys that examine perception from a truly unified vision-language perspective -- one that treats vision and language as an inseparable modality. Existing reviews are often fragmented, focusing separately on either vision or language, and thus rarely capture the cross-modal evolution of perception as an integrated capability. To bridge this gap, we present the first systematic survey of unified vision-language perception in MLLMs.
Specifically, we (1) formalize MLLM perception as an intrinsic, unified vision-language capability analogous to human innate perception, (2) introduce a five-stage taxonomy tracing the paradigm evolution of MLLM perception and survey representative methods and milestones at each phase, and (3) identify open challenges and outline promising research directions toward truly general, unified multimodal intelligence.
We hope our study will provide both a foundational understanding and an actionable roadmap to foster further innovation on the path toward artificial general intelligence (AGI).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Quantifying Prior Dominance in Systems
The study introduces the Normalized Context Utilization (NCU) metric to evaluate Retrieval-Augmented Generation (RAG) systems, revealing that Small Language Models (SLMs) outperform larger models in factual extraction. The findings indicate that traditional scaling laws yield diminishing returns, with a commercial API frequently failing against adversarial evidence due to systemic confidence collapse.