English

COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models

Machine Learning 2024-10-01 v1 Artificial Intelligence Computer Vision and Pattern Recognition Graphics

Abstract

We propose a novel framework COLLAGE for generating collaborative agent-object-agent interactions by leveraging large language models (LLMs) and hierarchical motion-specific vector-quantized variational autoencoders (VQ-VAEs). Our model addresses the lack of rich datasets in this domain by incorporating the knowledge and reasoning abilities of LLMs to guide a generative diffusion model. The hierarchical VQ-VAE architecture captures different motion-specific characteristics at multiple levels of abstraction, avoiding redundant concepts and enabling efficient multi-resolution representation. We introduce a diffusion model that operates in the latent space and incorporates LLM-generated motion planning cues to guide the denoising process, resulting in prompt-specific motion generation with greater control and diversity. Experimental results on the CORE-4D, and InterHuman datasets demonstrate the effectiveness of our approach in generating realistic and diverse collaborative human-object-human interactions, outperforming state-of-the-art methods. Our work opens up new possibilities for modeling complex interactions in various domains, such as robotics, graphics and computer vision.

Keywords

Cite

@article{arxiv.2409.20502,
  title  = {COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models},
  author = {Divyanshu Daiya and Damon Conover and Aniket Bera},
  journal= {arXiv preprint arXiv:2409.20502},
  year   = {2024}
}

Comments

9 pages, 6 figures

R2 v1 2026-06-28T19:02:39.110Z