A study compared the vulnerability of C programs generated by nine state-of-the-art Large Language Models (LLMs) using a zero-shot prompt. The researchers introduced FormAI-v2, a dataset of 331,000 C programs generated by these LLMs, and found that at least 62.07% of the generated programs contained vulnerabilities, detected via formal verification. The research highlights the need for risk assessment and validation when deploying LLM-generated code in production environments.
This paper introduces ProgramFC, a fact-checking model that decomposes complex claims into simpler sub-tasks using a library of functions. The model uses LLMs to generate reasoning programs and executes them by delegating sub-tasks, enhancing explainability and data efficiency. Experiments on fact-checking datasets demonstrate ProgramFC's superior performance compared to baseline methods, with publicly available code and data.
This paper introduces two methods for creating Arabic LLM prompts at scale: translating existing English prompt datasets and creating natural language prompts from Arabic NLP datasets. Using these methods, the authors generated over 67.4 million Arabic prompts covering tasks like summarization and question answering. Fine-tuning a 7B Qwen2 model on these prompts outperforms a 70B Llama3 model in handling Arabic prompts. Why it matters: The research provides a cost-effective approach to scaling Arabic LLM training data, potentially improving the performance of smaller, more accessible models for Arabic NLP.
MBZUAI researchers introduce Web2Code, a new large-scale dataset and evaluation framework for training and benchmarking multimodal LLMs on webpage understanding and HTML code generation. The dataset includes webpage images, HTML code, and QA pairs about webpage content. Experiments demonstrate the dataset's utility in webpage understanding, code generation, and general visual domain tasks, with code and data available on Github.
VinAI Research presented research projects focused on advancing image generation and manipulation using GANs and Diffusion Models. The research aims to improve GANs regarding utility, coverage, and output consistency. For Diffusion Models, the work focuses on improving the models’ speed to approach real-time performance and prevent negative social impact of diffusion-based personalized text-to-image generation. Why it matters: This talk indicates ongoing research and development in generative AI in Southeast Asia, an area of growing interest globally.
Ekaterina Radionova from Smarter AI (formerly Samsung AI Center) presented an approach to generating lifelike real-time avatars. The work focuses on generating high-quality video with authentic facial features to support online generation. Radionova's master's degree is from Skoltech on Data Science program and Bachelor degree at Moscow Institute of Physics and Technology on Applied Math. Why it matters: Achieving realistic real-time avatars is critical for applications in online communication, entertainment, and virtual reality within the region.
KAUST held its second hackathon and third NVIDIA workshop. Attendees listened to lectures from international experts. Participants worked on porting their scientific applications to a GPU accelerator. Why it matters: Such events help build regional expertise in accelerated computing and attract international collaboration.