# LMEye: An Interactive Perception Network for Large Language Models

arXiv: https://arxiv.org/abs/2305.03701 · HTML: https://mlsanity.com/paper/2305.03701/

## Key facts

- Cited by 27 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 43 of its 81 references that are in the map.
- First posted on arXiv 5 May 2023.

## 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 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [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)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)

## Built on by (most cited first, 27 of 27)

- [Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts](https://mlsanity.com/paper/2405.11273/) (2024)
- [LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge](https://mlsanity.com/paper/2311.11860/) (2023)
- [VideoVista: A Versatile Benchmark for Video Understanding and Reasoning](https://mlsanity.com/paper/2406.11303/) (2024)
- [Large Language Models for Education: A Survey](https://mlsanity.com/paper/2405.13001/) (2024)
- [VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context](https://mlsanity.com/paper/2405.04950/) (2024)
- [Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey](https://mlsanity.com/paper/2312.16602/) (2023)
- [Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey](https://mlsanity.com/paper/2412.18619/) (2024)
- [Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models](https://mlsanity.com/paper/2403.07304/) (2024)
- [A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering](https://mlsanity.com/paper/2311.07536/) (2023)
- [Temporal Knowledge Question Answering via Abstract Reasoning Induction](https://mlsanity.com/paper/2311.09149/) (2023)
- [Vision-Language Instruction Tuning: A Review and Analysis](https://mlsanity.com/paper/2311.08172/) (2023)
- [FlexVLN: Flexible Adaptation for Diverse Vision-and-Language Navigation Tasks](https://mlsanity.com/paper/2503.13966/) (2025)
- [Visual Position Prompt for MLLM based Visual Grounding](https://mlsanity.com/paper/2503.15426/) (2025)
- [Path to Medical AGI: Unify Domain-specific Medical LLMs with the Lowest Cost](https://mlsanity.com/paper/2306.10765/) (2023)
- [Training Multimedia Event Extraction With Generated Images and Captions](https://mlsanity.com/paper/2306.08966/) (2023)
- [Multimodal Large Models Are Effective Action Anticipators](https://mlsanity.com/paper/2501.00795/) (2025)
- [Where, What, Why: Towards Explainable Driver Attention Prediction](https://mlsanity.com/paper/2506.23088/) (2025)
- [Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use](https://mlsanity.com/paper/2403.02626/) (2024)
- [Testing the Depth of ChatGPT's Comprehension via Cross-Modal Tasks Based on ASCII-Art: GPT3.5's Abilities in Regard to Recognizing and Generating ASCII-Art Are Not Totally Lacking](https://mlsanity.com/paper/2307.16806/) (2023)
- [LLMI3D: MLLM-based 3D Perception from a Single 2D Image](https://mlsanity.com/paper/2408.07422/) (2024)
- [SwitchGPT: Adapting Large Language Models for Non-Text Outputs](https://mlsanity.com/paper/2309.07623/) (2023)
- [Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs](https://mlsanity.com/paper/2311.15759/) (2023)
- [Mitigating Multilingual Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2408.00550/) (2024)
- [Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models](https://mlsanity.com/paper/2404.10357/) (2024)
- [Cross-domain Multi-step Thinking: Zero-shot Fine-grained Traffic Sign Recognition in the Wild](https://mlsanity.com/paper/2409.01534/) (2024)
- [Sparrow: Data-Efficient Video-LLM with Text-to-Image Augmentation](https://mlsanity.com/paper/2411.19951/) (2024)
- [An Enhanced Large Language Model For Cross Modal Query Understanding System Using DL-KeyBERT Based CAZSSCL-MPGPT](https://mlsanity.com/paper/2502.17000/) (2025)

## Abstract (arXiv)

Training a Multimodal Large Language Model (MLLM) from scratch, like GPT-4, is resource-intensive. Regarding Large Language Models (LLMs) as the core processor for multimodal information, our paper introduces LMEye, a human-like eye with a play-and-plug interactive perception network, designed to enable dynamic interaction between LLMs and external vision information. Previous methods incorporate visual information into LLMs with a simple visual mapping network or Q-former from BLIP-2. Such networks project the image feature once yet do not consider the interaction between the image and the human input query. Hence, the obtained visual information without being connected to human intention may be inadequate for LLMs to generate intention-following responses, which we refer to as static visual information. LMEye addresses this issue by allowing the LLM to request the desired visual information aligned with various human instructions, which we term as the dynamic visual information interaction. Specifically, LMEye consists of a simple visual mapping network to provide the basic perception of an image for LLMs. It also contains additional modules responsible for acquiring requests from LLMs, performing request-based visual information interaction, and transmitting the resulting interacted visual information to LLMs, respectively. In this way, LLMs act to understand the human query, deliver the corresponding request to the request-based visual information interaction module, and generate the response based on the interleaved multimodal information. We evaluate LMEye through extensive experiments on some multimodal benchmarks, demonstrating that it significantly improves the zero-shot performance on various multimodal tasks compared to previous methods, with less parameters.