LLM-Driven “Coach-Athlete” Pretraining Framework for Complex Text-To-Motion Generation

J Fu, Y Long, X Wang, J Yin - 2024 International Joint …, 2024 - ieeexplore.ieee.org
Advanced text-to-motion models should one by one generate all sub-actions in the complex
motion following the given motion description. Existing text-to-motion models have …

Improving Situated Conversational Agents with Step-by-Step Multi-modal Logic Reasoning

Y Long, H Zhang, B Hui, Z Yang, C Yuan… - Proceedings of The …, 2023 - aclanthology.org
To fulfill complex user requirements in a situated conversational scenario, the agent needs
to conduct step-by-step multi-modal logic reasoning, which includes locating objects …

Foundation Models for Robotics: Best Known Practices

X Shaocong, Z Hao - Proceedings of the 22nd Chinese National …, 2023 - aclanthology.org
Abstract “Artificial general intelligence (AGI) used to be a sci-fi word but recently the
surprising general-ization capability of foundation models have triggered a lot of attention to …