What is a Multimodal LLM?

Introduction

Multimodal is the ability for a model to process several different types of inputs. For example, ChatGPT can support text input as well as image input as one combined input. You could also have a model take in .pdf, .md, and input text as inputs (yes, these count as different modalities). 

This allows for users to give represent different ideas in its rawest form possible, such as an image, instead of describing it. If you try to describe it, you could hit hurdles in trying to properly explain it and making sure it interpreted the description correctly. 

How do Multimodal LLMs work? 

Typically, these modalities are "fused" together. Here's an architecture diagram, 
Image from NVIDIA

In this case, we have an encoder for a specific modality (e.g. video encoder, image encoder, audio encoder). This encodes them into embeddings the LLM can understand and use. After encoding each specific modality, we then fuse them together. Then, the output is projected and then uses the needed modality generator to generate the specific modality needed (text-based, image-based, etc.). These could point to a Diffusion/Image generation model, a text-decoder model, etc.

What is "Fusing"?

Fusing is a term for how we add things together. For example, you can map all the features from the different modalities into one shared latent space that the LLM understands. For example, we could have pre-trained encoders (ResNet-50), and map all of them together through a Linear Layer, Attention Layer, etc. to one embedding space. This space would not only encapsulate all the data from the encoders, but it would also be trained to embed vectors in a way LLM would understand (Huang et. al. 2024). 

Use Cases

1. Image-Text Questions: Some abstract ideas can only be shown through images. Sometimes, these abstract ideas don't make sense (does this person look mad? confused?), and can't be expressed by words. In this scenario, we can use a Large Multimodal Model. 

2. Radiology Imaging: Radiologists can input in an X-ray, MRI, text-query, and more. The model can then be prompted with specific questions and conduct specific tasks to look over the reports, saving radiologists time (Haq et. al. 2025). 

Comments

Post a Comment

Popular posts from this blog

Top 3 Breakthroughs in Computer Vision in 2024

Image
Introduction Over the past few year, AI has become popular; however, no year matches the pace of the past few years. 2024 was an extremely crucial year for Computer Vision, with new models and breakthroughs occurring rapidly. Today, I'll be talking about the 3 biggest advancements in the Computer Vision field during 2024.  3. Vision Language Modeling Simply put, Vision Language Models, or VLMs for short, are Large Language Models (LLMs) that take an image and/or text as input. Think of ChatGPT, where you import an image and then type out a question that you have over the image. It will be able to understand both and output an answer. These are also what you would call a "multimodal model," which is a model that can understand multiple different types of sources/inputs.  Although Vision Language Models have existed for a while, they have recently become better and more accurate. However, this doesn't mean it's all sunshine an rainbows: there are still several barri...
Read more

A Mathematical Explanation of Gradient Descent

Image
Example of a close-to-optimal Gradient descent for a quadratic function. Credit: Dylan Introduction Although I wrote an article recently explaining Gradient Descent, I feel like a mathematical explanation of how it works would be beneficial not only to understand how it works, but also how you derive the functions.  Explanation First, we need a way to calculate how far off the model is. For our example, we will use the L2 Loss Function,  Let N represent the total amount of data points we have, i the iteration we are on, yᵢ represent the expected output, and ŷ represent the output predicted by the model.  Let's look more into ŷ. Since ŷ is the predicted value, this is the function that needs to have their parameters changed. Our goal is to change these parameters enough to minimize the loss of ŷ. For our example, let's set ŷ to be a linear line.  The values in "a" and "b" are our parameters. These will be the values we will have to change within f(x) to chang...
Read more