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 …
motion following the given motion description. Existing text-to-motion models have …
Improving Situated Conversational Agents with Step-by-Step Multi-modal Logic Reasoning
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 …
to conduct step-by-step multi-modal logic reasoning, which includes locating objects …
Foundation Models for Robotics: Best Known Practices
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 …
surprising general-ization capability of foundation models have triggered a lot of attention to …