Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models

This article introduces a research paper on generating full-body human-human interactions using autoregressive diffusion models. The focus is on a novel approach to modeling and generating complex human interactions, likely addressing challenges in realism and coherence. The use of autoregressive diffusion models suggests an attempt to capture the sequential and probabilistic nature of human movements and interactions. Further analysis would require examining the specific methods, datasets, and evaluation metrics used in the research.