Jorge Amador, a PhD student at KAUST's Visual Computing Center, presented a talk on physically-based simulation for generative AI models. The talk covered the use of synthetic data generation and physical priors to address the need for high-quality datasets. Applications discussed include photo editing, navigation, digital humans, and cosmological simulations. Why it matters: This research explores a promising technique to overcome data scarcity issues in AI, particularly relevant in resource-constrained environments or for sensitive applications.
Fudan University's Zhongyu Wei presented research on social simulation driven by LLMs, covering individual and large-scale social movement simulation. Wei directs the Data Intelligence and Social Computing Lab (Fudan DISC) and has published extensively on multimodal large models and social computing. His work includes the Volcano multimodal model, DISC-MedLLM, and ElectionSim. Why it matters: Using LLMs for social simulation could provide new tools for understanding and potentially predicting social dynamics in the Arab world.
KAUST professor David Ketcheson uses mathematical modeling to understand COVID-19 transmission. He applies differential equations to explain the progression of SARS-CoV-2, utilizing the SIR model to predict the spread. Ketcheson's analysis suggests that the reproduction number for COVID-19 could be as high as 5, emphasizing the need for social distancing. Why it matters: This highlights the role of mathematical modeling and data analysis in understanding and predicting the spread of infectious diseases, particularly in the context of pandemic response.
MBZUAI's Professor Le Song is developing an AI-driven simulation to model the human body at societal, organ, tissue, cellular, and molecular levels. The goal is to reduce the time and cost associated with bringing new medicines to market by removing the need for wet lab biological research. Song aims to create a comprehensive model using machine learning. Why it matters: This research could revolutionize drug discovery in the region by accelerating the development process and reducing reliance on traditional research methods.
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.