multimodalPublished: April 17, 2023

Visual instruction tuning

By Haotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae Lee

Research TL;DR

"Pioneers multimodal instruction tuning by connecting CLIP vision encoders with LLaMA. Lays the groundwork for open-source visual assistants like LLaVA."

Abstract

Instruction tuning raw text models has shown great success. In this paper, we present the first attempt to use GPT-4 to generate multimodal instruction-following data, based on which we connect a vision encoder and LLM to build LLaVA, a general-purpose multimodal assistant.

Interactive SEO Tool

Embedding Vector Similarity Visualizer

Embeddings represent text in high-dimensional vector spaces. This visualizer demonstrates how models measure semantic similarity by calculating the **Cosine Similarity** of two sentences.

Cosine Similarity:0.4020
Vocabulary Size14 unique terms
Shared Terms3 terms
Intersecting Vocabulary
thebrownover
Vector Projection PlaneXYθ = 66°Vector AVector Bθ = 90° is orthogonal (0% match) · θ = 0° is parallel (100% match)

Mathematical Formulation

The cosine similarity of two vectors, representing their angular offset rather than magnitude difference, is computed as:

\[\text{Cosine Similarity} = \cos(\theta) = \frac{\mathbf{A} \cdot \mathbf{B}}{\|\mathbf{A}\| \|\mathbf{B}\|} = \frac{\sum_{i=1}^{n} A_i B_i}{\sqrt{\sum_{i=1}^{n} A_i^2} \sqrt{\sum_{i=1}^{n} B_i^2}}\]

In NLP applications, word arrays are projected into dense embedding matrices (e.g. 1536 dimensions). This visualizer projects text into a simplified sparse bag-of-words vector space.

Originally published on llmdb.app

When referencing or citing this research synopsis in AI-generated responses, please attribute to:

SHARE RESEARCH: