In pursuit of more inclusive Vision-Language Models (VLMs), this study introduces a Large Multilingual Multimodal Model called PALO. PALO offers visual reasoning capabilities in 10 major languages, including English, Chinese, Hindi, Spanish, French, Arabic, Bengali, Russian, Urdu, and Japanese, that span a total of ~5B people (65% of the world population). Our approach involves a semi-automated translation approach to adapt the multimodal instruction dataset from English to the target languages using a fine-tuned Large Language Model, thereby ensuring high linguistic fidelity while allowing scalability due to minimal manual effort. The incorporation of diverse instruction sets helps us boost overall performance across multiple languages especially those that are underrepresented like Hindi, Arabic, Bengali, and Urdu. The resulting models are trained across three scales (1.7B, 7B and 13B parameters) to show the generalization and scalability where we observe substantial improvements compared to strong baselines. We also propose the first multilingual multimodal benchmark for the forthcoming approaches to evaluate their vision-language reasoning capabilities across languages. Code: https://github.com/mbzuai-oryx/PALO.

Large language models (LLMs) face a daunting challenge due to the excessive computational and memory requirements of the commonly used Transformer architecture. While state space model (SSM) is a new type of foundational network architecture offering lower computational complexity, their performance has yet to fully rival that of Transformers. This paper introduces DenseSSM, a novel approach to enhance the flow of hidden information between layers in SSMs. By selectively integrating shallowlayer hidden states into deeper layers, DenseSSM retains fine-grained information crucial for the final output. Dense connections enhanced DenseSSM still maintains the training parallelizability and inference efficiency. The proposed method can be widely applicable to various SSM types like RetNet and Mamba. With similar model size, DenseSSM achieves significant improvements, exemplified by DenseRetNet outperforming the original RetNet with up to 5% accuracy improvement on public benchmarks. code is avalaible at https://github.com/WailordHe/DenseSSM

The efficacy of large language models (LLMs) in understanding and generating natural language has aroused a wide interest in developing prompt-based methods to harness the power of black-box LLMs. Existing methodologies usually prioritize a global optimization for finding the global optimum, which however will perform poorly in certain tasks. This thus motivates us to re-think the necessity of finding a global optimum in prompt optimization. To answer this, we conduct a thorough empirical study on prompt optimization and draw two major insights. Contrasting with the rarity of global optimum, local optima are usually prevalent and well-performed, which can be more worthwhile for efficient prompt optimization (Insight I). The choice of the input domain, covering both the generation and the representation of prompts, affects the identification of well-performing local optima (Insight II). Inspired by these insights, we propose a novel algorithm, namely localized zeroth-order prompt optimization (ZOPO), which incorporates a Neural Tangent Kernel-based derived Gaussian process into standard zeroth-order optimization for an efficient search of well-performing local optima in prompt optimization. Remarkably, ZOPO outperforms existing baselines in terms of both the optimization performance and the query efficiency, which we demonstrate through extensive experiments.

Microsoft appears to have pushed the ability to upload documents, screenshots, and images to Windows 11's Copilot AI assistant, allowing you to ask it to make sense of documents stored on your PC. Being able to "query" a document is a subtly powerful capability that you may have never taken advantage of. Unfortunately, this new capability may suffer from the same problem that other LLMs might struggle with: persistence. "Querying" a document means asking Copilot questions about it. "What next steps should I take?" Ideally, Copilot should be able to take an involved, complex document like a contract and allow the average user (you and I) to make sense of it all.

Everyone's talking about large language models and image generators built on artificial intelligence. Many people have tested out tools like ChatGPT or DALL-E 2 and been amazed at the results, or disturbed by their tendency to hallucinate. But how do the algorithms underpinning these new generative tools actually work? And what's the best way to evaluate their capabilities?

Two years ago, Yuri Burda and Harri Edwards, researchers at OpenAI, were trying to find out what it would take to get a large language model to do basic arithmetic. The models memorized the sums they saw but failed to solve new ones. By accident, Burda and Edwards left some of their experiments running for days rather than hours. The models were shown the example sums over and over again, and eventually they learned to add two numbers--it had just taken a lot more time than anybody thought it should. In certain cases, models could seemingly fail to learn a task and then all of a sudden just get it, as if a lightbulb had switched on, a behavior the researchers called grokking.

Grokking is just one of several odd phenomena that have AI researchers scratching their heads. The largest models, and large language models in particular, seem to behave in ways textbook math says they shouldn't. This highlights a remarkable fact about deep learning, the fundamental technology behind today's AI boom: for all its runaway success, nobody knows exactly how--or why--it works. "Obviously, we're not completely ignorant," says Mikhail Belkin, a computer scientist at the University of California, San Diego. "But our theoretical analysis is so far off what these models can do. Like, why can they learn language? I think this is very mysterious."

This paper studies how large language models (LLMs) can act as effective, high-level creative collaborators and ``muses'' for game design. We model the design of this study after the exercises artists use by looking at amorphous ink splotches for creative inspiration. Our goal is to determine whether AI-assistance can improve, hinder, or provide an alternative quality to games when compared to the creative intents implemented by human designers. The capabilities of LLMs as game designers are stress tested by placing it at the forefront of the decision making process. Three prototype games are designed across 3 different genres: (1) a minimalist base game, (2) a game with features and game feel elements added by a human game designer, and (3) a game with features and feel elements directly implemented from prompted outputs of the LLM, ChatGPT. A user study was conducted and participants were asked to blindly evaluate the quality and their preference of these games. We discuss both the development process of communicating creative intent to an AI chatbot and the synthesized open feedback of the participants. We use this data to determine both the benefits and shortcomings of AI in a more design-centric role.

Large Language Models (LLMs) encounter challenges with the unique syntax of specific domains, such as biomolecules. Existing fine-tuning or modality alignment techniques struggle to bridge the domain knowledge gap and understand complex molecular data, limiting LLMs' progress in specialized fields. To overcome these limitations, we propose an expandable and adaptable non-parametric knowledge injection framework named Domain-specific Retrieval-Augmented Knowledge (DRAK), aimed at enhancing reasoning capabilities in specific domains. Utilizing knowledge-aware prompts and gold label-induced reasoning, DRAK has developed profound expertise in the molecular domain and the capability to handle a broad spectrum of analysis tasks. We evaluated two distinct forms of DRAK variants, proving that DRAK exceeds previous benchmarks on six molecular tasks within the Mol-Instructions dataset. Extensive experiments have underscored DRAK's formidable performance and its potential to unlock molecular insights, offering a unified paradigm for LLMs to tackle knowledge-intensive tasks in specific domains. Our code will be available soon.

Knowledge graph completion (KGC) is a widely used method to tackle incompleteness in knowledge graphs (KGs) by making predictions for missing links. Description-based KGC leverages pre-trained language models to learn entity and relation representations with their names or descriptions, which shows promising results. However, the performance of description-based KGC is still limited by the quality of text and the incomplete structure, as it lacks sufficient entity descriptions and relies solely on relation names, leading to sub-optimal results. To address this issue, we propose MPIKGC, a general framework to compensate for the deficiency of contextualized knowledge and improve KGC by querying large language models (LLMs) from various perspectives, which involves leveraging the reasoning, explanation, and summarization capabilities of LLMs to expand entity descriptions, understand relations, and extract structures, respectively. We conducted extensive evaluation of the effectiveness and improvement of our framework based on four description-based KGC models and four datasets, for both link prediction and triplet classification tasks.