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.
This paper introduces a virtual wheel-terrain interaction model developed and validated for the UAE Rashid rover to enhance simulation accuracy for space rovers. The model incorporates wheel grouser properties, slippage, soil properties, and interaction mechanics, validated via lunar soil simulation. Experiments tested a Grouser-Rashid rover wheel at slip ratios of 0, 0.25, 0.50, and 0.75. Why it matters: This simulation method advances rover design and control, crucial for the UAE's space exploration program and lunar mission success.
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.
KAUST's Core Labs provide engineering simulation services and training using state-of-the-art technology. The Supercomputing Core Lab (KSL) at KAUST conducts training workshops in partnership with ANSYS, a market leader in engineering and simulation design software. Since 2017, KSL has conducted five training workshops related to engineering software in partnership with ANSYS, with 230 attendees, including 138 individuals from in-Kingdom institutions outside of KAUST. Why it matters: These workshops strengthen Saudi Arabia's engineering capabilities by providing access to simulation software and training, facilitating collaboration between KAUST, Saudi Aramco, and SABIC.
MBZUAI researchers developed MedAgentSim, a simulated hospital environment to evaluate AI diagnostic abilities. The simulation uses LLM-powered agents to mimic doctor-patient conversations, providing a dynamic assessment of diagnostic skills. The system includes doctor, patient, and evaluator agents that interact within the simulated hospital, making real-time decisions. Why it matters: This research offers a more realistic evaluation of AI in clinical settings, addressing limitations of current benchmarks and potentially improving AI's use in healthcare.