Researchers have developed Uni-HOI, a unified framework designed to model the complex interactions between humans, objects, and text. This system integrates large language models with specialized VQ-VAEs to process diverse motion data into a format compatible with LLMs. Uni-HOI employs a two-stage training process, first learning correlations across modalities and then fine-tuning for specific tasks, demonstrating strong performance in areas like text-driven HOI generation and motion prediction. AI
影响 Enables more sophisticated virtual and mixed-reality applications by unifying text and motion data.
排序理由 Academic paper introducing a new framework for modeling human-object interactions.
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
