Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Voice2Action: Language Models as Agent for Efficient Real-Time Interaction in Virtual Reality (2310.00092v1)

Published 29 Sep 2023 in cs.CL, cs.AI, and cs.HC

Abstract: LLMs are trained and aligned to follow natural language instructions with only a handful of examples, and they are prompted as task-driven autonomous agents to adapt to various sources of execution environments. However, deploying agent LLMs in virtual reality (VR) has been challenging due to the lack of efficiency in online interactions and the complex manipulation categories in 3D environments. In this work, we propose Voice2Action, a framework that hierarchically analyzes customized voice signals and textual commands through action and entity extraction and divides the execution tasks into canonical interaction subsets in real-time with error prevention from environment feedback. Experiment results in an urban engineering VR environment with synthetic instruction data show that Voice2Action can perform more efficiently and accurately than approaches without optimizations.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (9)
  1. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  2. Inner monologue: Embodied reasoning through planning with language models. arXiv preprint arXiv:2207.05608.
  3. 3D user interfaces: theory and practice. Addison-Wesley Professional.
  4. Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332.
  5. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730–27744.
  6. Toolformer: Language models can teach themselves to use tools. arXiv preprint arXiv:2302.04761.
  7. Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface. arXiv preprint arXiv:2303.17580.
  8. Self-instruct: Aligning language model with self generated instructions. arXiv preprint arXiv:2212.10560.
  9. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (1)
  1. Yang Su (147 papers)
Citations (1)