Summary of Aligned Vector Quantization For Edge-cloud Collabrative Vision-language Models, by Xiao Liu et al.
Aligned Vector Quantization for Edge-Cloud Collabrative Vision-Language Models
by Xiao Liu, Lijun Zhang, Deepak Ganesan, Hui Guan
First submitted to arxiv on: 8 Nov 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 This paper introduces LLaVA-AlignedVQ, an edge-cloud collaborative Visual Question Answering (VQA) system that leverages a novel Aligned Vector Quantization algorithm (AlignedVQ) for efficient compression of intermediate features. The system achieves approximately 1365x compression rate, reducing data transmission overhead by 96.8% compared to transmitting JPEG90-compressed images to the cloud. LLaVA-AlignedVQ also achieves an inference speedup of 2-15x while maintaining high accuracy, comparable to the original model’s performance across eight VQA datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper makes it possible for computers to work together and answer questions about pictures. It shows how to make a special kind of computer model that can be used on devices like smartphones or tablets, rather than just in big cloud computers. This helps reduce the amount of data sent over the internet and makes the process faster. The new system is good at answering questions and works almost as well as the original version. |
Keywords
» Artificial intelligence » Inference » Quantization » Question answering
