From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models
Haoxiang Sun, Tao Wang, Li Yuan, Jian Zhao, Jiancheng Lv
Why It Matters
What makes this one worth your time
Understanding the evolution of vision-language perception in MLLMs can guide researchers in developing more integrated and advanced multimodal AI systems.
A systematic survey of unified vision-language perception in MLLMs with a proposed taxonomy and future directions.
Summary
The paper presents a systematic survey of the evolution of vision-language perception paradigms in multimodal large language models (MLLMs), proposing a unified perspective that treats vision and language as inseparable modalities. It introduces a five-stage taxonomy of MLLM perception evolution, surveys representative methods and milestones, and identifies open challenges and future research directions.
Key contributions
- Proposes a unified vision-language perspective for MLLM perception.
- Introduces a five-stage taxonomy of MLLM perception evolution.
- Identifies open challenges and outlines future research directions.
Notable insights
- The paper formalizes MLLM perception as an intrinsic, unified vision-language capability analogous to human perception.
- It introduces a five-stage taxonomy to trace the evolution of MLLM perception paradigms.
Possible limitations
- Not stated in the abstract
Abstract
arXiv:2606.26196v1 Announce Type: cross 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).