Researchers from MBZUAI, UC Berkeley, CMU, Stanford, and UC San Diego collaborated to create Vicuna, an open-source chatbot that costs $300 to train, unlike ChatGPT which costs over $4 million. Vicuna achieves 90% of ChatGPT's subjective language quality while being far more energy-efficient and can run on a single GPU. It was fine-tuned from Meta AI’s LLaMA model using user-shared conversations and has gained significant traction on GitHub. Why it matters: This research demonstrates that high-quality chatbots can be developed at a fraction of the cost and environmental impact, opening up new possibilities for sustainable AI development in the region.
MBZUAI President Eric Xing led a global collaboration to develop Vicuna, an LLM alternative to GPT-3 addressing the unsustainable costs of training LLMs. OpenAI CEO Sam Altman acknowledged Abu Dhabi's role in the global AI conversation, building off of achievements like Vicuna. Xing and colleagues are publishing research at MLSys 2023 on "cross-mesh resharding" to improve computer communication in deep learning, aiming for low-carbon, affordable, and miniaturized AI. Why it matters: This research signals a push towards sustainable AI development in the region, emphasizing efficiency and reduced environmental impact.
The paper introduces Juhaina, a 9.24B parameter Arabic-English bilingual LLM trained with an 8,192 token context window. It identifies limitations in the Open Arabic LLM Leaderboard (OALL) and proposes a new benchmark, CamelEval, for more comprehensive evaluation. Juhaina outperforms models like Llama and Gemma in generating helpful Arabic responses and understanding cultural nuances. Why it matters: This culturally-aligned LLM and associated benchmark could significantly advance Arabic NLP and democratize AI access for Arabic speakers.
Video-ChatGPT is a new multimodal model that combines a video-adapted visual encoder with a large language model (LLM) to enable detailed video understanding and conversation. The authors introduce a new dataset of 100,000 video-instruction pairs for training the model. They also develop a quantitative evaluation framework for video-based dialogue models.
MBZUAI increased faculty diversity and worked with global partners on application projects in 2023, including developing Jais (with Core42 and Cerebras) and Vicuna (with UC San Diego, UC Berkeley, CMU, and Stanford). They also launched Jais Climate, a bilingual LLM for climate intelligence, and LLM360, a framework for transparent LLM research. Why it matters: MBZUAI's involvement in open-source GenAI initiatives and partnerships positions the UAE as a key player in responsible AI development and talent creation.
MBZUAI has been actively involved in developing AI and generative models, contributing to models like Llama 2, Jais, Vicuna, and LaMini. Professor Preslav Nakov notes Llama 2's improvements in size and carbon footprint over Llama 1. MBZUAI aims to tackle challenges like information accuracy, economic costs, and the scarcity of Arabic online content. Why it matters: MBZUAI's work helps address the limitations of current LLMs, particularly for Arabic, and promotes sustainable AI development in the region.
A new benchmark, LongShOTBench, is introduced for evaluating multimodal reasoning and tool use in long videos, featuring open-ended questions and diagnostic rubrics. The benchmark addresses the limitations of existing datasets by combining temporal length and multimodal richness, using human-validated samples. LongShOTAgent, an agentic system, is also presented for analyzing long videos, with both the benchmark and agent demonstrating the challenges faced by state-of-the-art MLLMs.