Summary of Postdoc: Generating Poster From a Long Multimodal Document Using Deep Submodular Optimization, by Vijay Jaisankar et al.
PostDoc: Generating Poster from a Long Multimodal Document Using Deep Submodular Optimization
by Vijay Jaisankar, Sambaran Bandyopadhyay, Kalp Vyas, Varre Chaitanya, Shwetha Somasundaram
First submitted to arxiv on: 30 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL); 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 A novel deep submodular function is proposed for transforming long documents into posters. This challenging task involves summarizing the document’s content, generating a template, and harmonizing text and images. The function can be trained on ground truth summaries to extract multimodal content and ensure good coverage, diversity, and alignment of text and images. An LLM-based paraphraser is also used to generate a template with various design aspects conditioned on the input content. Extensive automated and human evaluations demonstrate the merits of this approach. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you have a long document that’s hard to read or understand. A poster is like a one-page summary that makes it easy to get the main points quickly. But how do we make this happen automatically? This paper shows how to take a long document and turn it into a nice-looking poster with text and images. It’s a tricky problem, but the solution involves training a special kind of function to extract important content from the document. Then, it uses a language model to create a template that fits the content perfectly. |
Keywords
* Artificial intelligence * Alignment * Language model
