Raluca Georgescu

Papers

Total Citations

H-Index

About

Raluca Georgescu is a rising researcher at the forefront of artificial intelligence, with a focus on generative models, human behavior imitation, and the scaling of embodied agents. Her work bridges the gap between generative AI and sequential decision-making, exploring how models like diffusion processes can replicate the rich, multimodal, and stochastic nature of human actions. In her highly cited 2023 paper, “Imitating Human Behaviour with Diffusion Models” (23 citations), she pioneered the use of diffusion models as observation-to-action systems, demonstrating their ability to capture complex behavioral correlations in sequential environments—a significant departure from traditional deterministic imitation learning. More recently, in “Scaling Laws for Pre-training Agents and World Models” (2024), she investigates how increasing model parameters, dataset size, and compute improves the performance of embodied agents across domains like robotics and video games. Her work is foundational for developing more human-like, scalable AI systems, with implications for autonomous agents that learn from offline data. Georgescu’s research is already shaping how the AI community approaches pre-training for behavior modeling, marking her as a key voice in the next wave of generative and agentic AI.