Thomas Hayes

Papers

Total Citations

H-Index

About

Thomas Hayes is an innovative researcher working at the forefront of generative AI, with a particular focus on text-conditional 3D human motion generation. His most recognized work, "Make-An-Animation" (2023), demonstrates his expertise in applying diffusion models to the challenging problem of synthesizing realistic human motion from natural language descriptions — a capability with far-reaching implications for animation, robotics, and virtual reality development. By leveraging large-scale training paradigms and advanced diffusion-based architectures, Hayes has helped push the boundaries of what's possible when bridging the gap between linguistic intent and physically plausible human movement. The paper has already accumulated 40 citations since its publication, reflecting the research community's rapid recognition of its significance in a highly competitive space. His contributions are particularly timely, as the field of controllable motion generation has emerged as a critical enabler for next-generation digital humans, game development pipelines, and autonomous robotic systems. For students and researchers exploring the intersection of natural language processing, computer vision, and generative modeling, Hayes's work represents an important and accessible entry point into cutting-edge motion synthesis research.