'Learning with AI' is an open-source book from the University of Leeds . We spoke with Chrissi Nerantzi, part of the project team about their choice to use Ariyana Ahmad's illustration'AI is Everywhere' for the cover of the book. For the team, the choice of cover was about more than just visual aesthetic. Collages can capture multiple perspectives, textures, and approaches, much like the student voices incorporated throughout the book. Ahmad's illustration, while not a collage, achieves a similar effect.

Large multimodal models still struggle with text-rich images because of inadequate training data. Self-Instruct provides an annotation-free way for generating instruction data, but its quality is poor, as multimodal alignment remains a hurdle even for the largest models. In this work, we propose LLaVAR-2, to enhance multimodal alignment for text-rich images through hybrid instruction generation between human annotators and large language models. Specifically, it involves detailed image captions from human annotators, followed by the use of these annotations in tailored text prompts for GPT-4o to curate a dataset. It also implements several mechanisms to filter out low-quality data, and the resulting dataset comprises 424k high-quality pairs of instructions. Empirical results show that models fine-tuned on this dataset exhibit impressive enhancements over those trained with self-instruct data.

Large multimodal language models have shown remarkable proficiency in understanding and editing images. However, a majority of these visually-tuned models struggle to comprehend the textual content embedded in images, primarily due to the limitation of training data. In this work, we introduce TRINS: a Text-Rich image INStruction dataset, with the objective of enhancing the reading ability of the multimodal large language model. TRINS is built upon LAION using hybrid data annotation strategies that include machine-assisted and human-assisted annotation processes. It contains 39,153 text-rich images, captions, and 102,437 questions. Specifically, we show that the number of words per annotation in TRINS is significantly longer than that of related datasets, providing new challenges. Furthermore, we introduce a simple and effective architecture, called a Language-vision Reading Assistant (LaRA), which is good at understanding textual content within images. LaRA outperforms existing state-of-the-art multimodal large language models on the TRINS dataset, as well as other classical benchmarks. Lastly, we conducted a comprehensive evaluation with TRINS on various text-rich image understanding and generation tasks, demonstrating its effectiveness.

An attractive book cover is important for the success of a book. In this paper, we apply Generative Adversarial Networks (GANs) to the book covers domain, using different methods for training in order to obtain better generated images. We interleave GANs with knowledge graphs to alter the input title to obtain multiple possible options for any given title, which are then used as an augmented input to the generator. Finally, we use the discriminator obtained during the training phase to select the best images generated with new titles. Our method performed better at generating book covers than previous attempts, and the knowledge graph gives better options to the book author or editor compared to using GANs alone.

When re-finding items, users who forget or are uncertain about identifying details often rely on creative strategies for expressing their information needs -- complex queries that describe content elements (e.g., book characters or events), information beyond the document text (e.g., descriptions of book covers), or personal context (e.g., when they read a book). This retrieval setting, called tip of the tongue (TOT), is especially challenging for models heavily reliant on lexical and semantic overlap between query and document text. In this work, we introduce a simple yet effective framework for handling such complex queries by decomposing the query into individual clues, routing those as sub-queries to specialized retrievers, and ensembling the results. This approach allows us to take advantage of off-the-shelf retrievers (e.g., CLIP for retrieving images of book covers) or incorporate retriever-specific logic (e.g., date constraints). We show that our framework incorportating query decompositions into retrievers can improve gold book recall up to 7% relative again for Recall@5 on a new collection of 14,441 real-world query-book pairs from an online community for resolving TOT inquiries.

AI and ChatGPT development should not be paused and neither should other large Artificial Intelligence experiments residents of Austin, Texas, told Fox News. In the tech world, AI means artificial intelligence. Many people would probably just scream it, "AIIIIIIIIIIIIIIIIIIIIIIIIII," out of fear of how big a threat it could become. Like it or not, new, "artificial intelligence" platforms like ChatGPT are going to change our lives in ways likely more monumental than the creation of the internet. News coverage of AI has been nothing short of apocalyptic.

Generative AI can help you write a rap song about your cat Fluffy in the style of Eminem. It can create a portrait of Elon Musk eating Hot Cheetos inside a rocket in space. But, can it do work tasks for us and produce finished products? Professionals across industries are experimenting with AI tools like ChatGPT, which produces conversational text using GPT-3 and GPT-4, and DALL-E, which creates images, to see if they might aid in their work. Creative jobs in industries such as marketing, writing, design and art may use AI to dream up ideas. Retail, sales and real estate sectors are trying to determine whether AI can speed up processes and get their products to market.

On June 1st, 2022, I received an email: "We're excited to have you as an early tester in the Midjourney Beta!" A week has now passed in what feels like a couple of hours. The image above was generated as a result of me writing a sentence filled with various descriptors about a yellow tent and a nature-filled landscape. As an artist, I've been cautiously curious about the application of AI learning to the creative industry. After finally dipping my toes into this pool by generating some prompts of my own, I was ready to swim.

Machine learning is getting mainstreamed as many organisations have integrated or are trying to integrate ML systems into their products and platforms. MLOps is the branch of ML that unifies ML systems development (dev) and ML systems deployments (ops). We have curated a list of top MLOps books to help you get a handle on the subject (in no particular order). The Machine Learning Engineering book is one of the most complete applied AI books out there and is filled with best practices and design patterns of building reliable machine learning solutions at scale. Andriy Burkov has a PhD in AI and is currently the machine learning team leader at Gartner.

Natural Language Programming or NLP has enabled computers to interpret human language that has further opened doors to new innovation. Due to this very reason, the interest to learn more about the subject has increased in recent years, and as they say, books are the best place to gather knowledge from. But when it comes to books, the options are in millions, and it is hard to zero-in on one. Also, people often tend to look for the ones freely available in the form of eBook or PDFs, which are quite hard to come by. In this article, we present to you the top 7 NLP books one can get their hands on for free.