Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation
원문 초록
We introduce Action-GPT, a plug-and-play framework for incorporating Large Language Models (LLMs) into text-based action generation models. Action phrases in current motion capture datasets contain minimal and to-the-point information. By carefully crafting prompts for LLMs, we generate richer and fine-grained descriptions of the action. We show that utilizing these detailed descriptions instead of the original action phrases leads to better alignment of text and motion spaces. We introduce a generic approach compatible with stochastic (e.g. VAE-based) and deterministic (e.g. MotionCLIP) text-to-motion models. In addition, the approach enables multiple text descriptions to be utilized. Our experiments show (i) noticeable qualitative and quantitative improvement in the quality of synthesized motions, (ii) benefits of utilizing multiple LLM-generated descriptions, (iii) suitability of the prompt function, and (iv) zero-shot generation capabilities of the proposed approach. Project page: https://actiongpt.github.io
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends
WorldVLA: Towards Autoregressive Action World Model
AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games
STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization
OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis
토론
이 논문과 연결된 포럼 글이 아직 없습니다.