Summary of Lmfusion: Adapting Pretrained Language Models For Multimodal Generation, by Weijia Shi et al.
LMFusion: Adapting Pretrained Language Models for Multimodal Generation
by Weijia Shi, Xiaochuang Han, Chunting Zhou, Weixin Liang, Xi Victoria Lin, Luke Zettlemoyer, Lili Yu
First submitted to arxiv on: 19 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary LMFusion is a novel framework that empowers pretrained large language models (LLMs) with multimodal generative capabilities. This framework leverages existing Llama-3’s weights and introduces additional transformer modules to process images using diffusion. During training, the data from each modality is processed independently by dedicated modules, while shared self-attention layers allow interactions across text and image features. By freezing the text-specific modules and only training the image-specific modules, LMFusion preserves the language capabilities of text-only LLMs while developing strong visual understanding and generation abilities. Experimental results demonstrate that LMFusion improves image understanding by 20% and image generation by 3.6% using only 50% of the FLOPs while maintaining Llama-3’s language capabilities. This framework not only leverages existing computational investments in text-only LLMs but also enables the parallel development of language and vision capabilities, presenting a promising direction for efficient multimodal model development. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Scientists have developed a new way to make computers understand and create both words and pictures. This is called LMFusion. It uses existing computer programs that are already good at understanding and creating text, but adds special tools to also understand and create images. The new system works by breaking down the tasks of processing text and images into smaller parts, then combining them in a way that lets the computer learn from both. This helps the computer become better at understanding and creating pictures while still being able to do its original job well. Tests show that this new system is 20% better at understanding pictures and 3.6% better at generating new ones. |
Keywords
» Artificial intelligence » Diffusion » Image generation » Llama » Self attention » Transformer
