Summary of Research on Personalized Compression Algorithm For Pre-trained Models Based on Homomorphic Entropy Increase, by Yicong Li et al.
Research on Personalized Compression Algorithm for Pre-trained Models Based on Homomorphic Entropy Increase
by Yicong Li, Xing Guo, Haohua Du
First submitted to arxiv on: 16 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 The paper explores the challenges and evolution of Vision Transformer and Large Language Model (LLM) in AI. The Vision Transformer captures global information by splitting images into small pieces, but its high reference count and compute overhead limit deployment on mobile devices. LLM has revolutionized natural language processing, but faces huge deployment challenges. To address these issues, the paper investigates model pruning techniques to reduce redundant parameters without losing accuracy for personalized data and resource-constrained environments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The Vision Transformer captures global information by splitting images into small pieces, but its high reference count and compute overhead limit deployment on mobile devices. The Large Language Model has revolutionized natural language processing, but faces huge deployment challenges. To address these issues, the paper investigates model pruning techniques to reduce redundant parameters without losing accuracy for personalized data and resource-constrained environments. |
Keywords
» Artificial intelligence » Large language model » Natural language processing » Pruning » Vision transformer
