# Visual Perception by Large Language Model's Weights

arXiv: https://arxiv.org/abs/2405.20339 · HTML: https://mlsanity.com/paper/2405.20339/

## Key facts

- Cited by 19 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 48 of its 62 references that are in the map.
- First posted on arXiv 30 May 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, 30 of 48)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)

## Built on by (most cited first, 19 of 19)

- [WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs](https://mlsanity.com/paper/2502.04326/) (2025)
- [Number it: Temporal Grounding Videos like Flipping Manga](https://mlsanity.com/paper/2411.10332/) (2024)
- [A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs](https://mlsanity.com/paper/2412.03324/) (2024)
- [Object Detection with Multimodal Large Vision-Language Models: An In-depth Review](https://mlsanity.com/paper/2508.19294/) (2025)
- [Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision](https://mlsanity.com/paper/2503.01879/) (2025)
- [CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms](https://mlsanity.com/paper/2505.17020/) (2025)
- [EE-MLLM: A Data-Efficient and Compute-Efficient Multimodal Large Language Model](https://mlsanity.com/paper/2408.11795/) (2024)
- [CoRA: Collaborative Information Perception by Large Language Model's Weights for Recommendation](https://mlsanity.com/paper/2408.10645/) (2024)
- [HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models](https://mlsanity.com/paper/2510.20322/) (2025)
- [EgoLCD: Egocentric Video Generation with Long Context Diffusion](https://mlsanity.com/paper/2512.04515/) (2025)
- [Taming LLMs by Scaling Learning Rates with Gradient Grouping](https://mlsanity.com/paper/2506.01049/) (2025)
- [Dynamic Embedding of Hierarchical Visual Features for Efficient Vision-Language Fine-Tuning](https://mlsanity.com/paper/2508.17638/) (2025)
- [You Only Forward Once: An Efficient Compositional Judging Paradigm](https://mlsanity.com/paper/2511.16600/) (2025)
- [Language-Pretraining-Induced Bias: A Strong Foundation for General Vision Tasks](https://mlsanity.com/paper/2604.01833/) (2026)
- [Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation](https://mlsanity.com/paper/2606.22429/) (2026)
- [Panther: Illuminate the Sight of Multimodal LLMs with Instruction-Guided Visual Prompts](https://mlsanity.com/paper/2411.13909/) (2024)
- [TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs](https://mlsanity.com/paper/2507.21584/) (2025)
- [AgroTools: A Benchmark for Tool-Augmented Multimodal Agents in Agriculture](https://mlsanity.com/paper/2605.22366/) (2026)
- [Dive Into the Implicit Biases of Low-rank Vision-language Alignment](https://mlsanity.com/paper/2607.08194/) (2026)

## Abstract (arXiv)

Existing Multimodal Large Language Models (MLLMs) follow the paradigm that perceives visual information by aligning visual features with the input space of Large Language Models (LLMs), and concatenating visual tokens with text tokens to form a unified sequence input for LLMs. These methods demonstrate promising results on various vision-language tasks but are limited by the high computational effort due to the extended input sequence resulting from the involvement of visual tokens. In this paper, instead of input space alignment, we propose a novel parameter space alignment paradigm that represents visual information as model weights. For each input image, we use a vision encoder to extract visual features, convert features into perceptual weights, and merge the perceptual weights with LLM's weights. In this way, the input of LLM does not require visual tokens, which reduces the length of the input sequence and greatly improves efficiency. Following this paradigm, we propose VLoRA with the perceptual weights generator. The perceptual weights generator is designed to convert visual features to perceptual weights with low-rank property, exhibiting a form similar to LoRA. The experimental results show that our VLoRA achieves comparable performance on various benchmarks for MLLMs, while significantly reducing the computational costs for both training and inference. The code and models will be made open-source.