智能体
arxiv.org ·
SalsaAgent：面向交互式舞蹈生成的多模态具身语言模型
该论文提出 SalsaAgent，一个根据人类领舞与音乐生成全身 salsa 跟舞动作的语言模型。方法将双人交互建模为非语言 token 传递，扩展 LLM 词表以处理离散动作 token、成对关系 token 与音频 token，并引入全身与成对关系 tokenizer，将语言与动作 token 与自动生成的骨架动态文本描述对齐，最后采用两阶段 token-to-diffusion 流程。主观与客观评测显示，其动作质量、双人空间协调以及音乐与舞伴协调性优于此前基线。
AI推荐理由 arXiv 正式论文（v3，2026-09-17 修订），来源可信、摘要信息密度高，明确给出方法构成（full-body 与 pairwise-relation tokenizer、语言-动作 token 对齐、两阶段 token-to-diffusion 流程）与评测维度（动作质量、双人空间协调、音乐与舞伴同步）。局限在于摘要仅称相对基线有提升，未给出具体指标或数值，也未提供代码与数据链接，实际效果无法从片段验证；应用场景偏具身人形机器人与社交交互，对通用 LLM/Agent 开发的直接迁移价值有限。
72
正文
Computer Science > Computer Vision and Pattern Recognition
arXiv:2605.29219 (cs)
[Submitted on 28 May 2026 (v1), last revised 17 Sep 2026 (this version, v3)]
Title:SalsaAgent: A multimodal embodied language model for interactive dance generation
Authors:Payam Jome Yazdian, Zoe Stanley, Angelica Lim
View a PDF of the paper titled SalsaAgent: A multimodal embodied language model for interactive dance generation, by Payam Jome Yazdian and 2 other authors
View PDF
HTML (experimental)
Abstract:Embodied interaction with humanoids depends on bidirectional nonverbal reactivity, coordination, and synchrony to convey cues and move with a partner. For socially interactive embodied agents, reactive motion generation requires expressive full-body motion that remains contextually appropriate while maintaining spatial and temporal synchrony. We present SalsaAgent, a language model that generates expressive, full-body salsa follower motions in reaction to a human leader and music. We formulate partner interaction as nonverbal token passing, extending the vocabulary of a large language model (LLM) to process discrete motion tokens, pairwise relation tokens, and audio tokens. Our method introduces full-body and pairwise-relation tokenizers, aligns language and motion tokens with automatically derived text descriptions of skeleton dynamics, and applies a two-stage token-to-diffusion pipeline. Subjective and objective evaluations show improved motion quality, two-person spatial coordination, and music and partner coordination relative to prior baselines.
Comments:
Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Cite as:
arXiv:2605.29219 [cs.CV]
(or
arXiv:2605.29219v3 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2605.29219
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Payam Jome Yazdian [view email]
[v1]
Thu, 28 May 2026 01:08:27 UTC (1,034 KB)
[v2]
Wed, 3 Jun 2026 18:14:15 UTC (1,034 KB)
[v3]
Thu, 17 Sep 2026 17:47:01 UTC (1,048 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled SalsaAgent: A multimodal embodied language model for interactive dance generation, by Payam Jome Yazdian and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new
|
recent
| 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)