Research map / Vision-language and multimodal / Human and embodied modeling
ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body
Juze Zhang, Changan Chen, Xin Chen, Heng Yu, Tiange Xiang, Ali Sartaz Khan, Shrinidhi K. Lakshmikanth, Ehsan Adeli
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use unified speech-language-behavior MoME model instead of co-speech gesture methods | ViBES · Converse3D benchmark | R1-Balanced: 0.323 -> 0.467 | Improved |
| use unified SLB model instead of text-to-motion baselines | ViBES · Converse3D benchmark | FID: 262.2 -> 93.9 | Improved |
| use unified SLB model instead of text-to-motion baselines | ViBES · Converse3D benchmark | R1-Conv: 0.524 -> 0.745 | Improved |
| add motion experts to GLM-4-Voice backbone for speech quality | ViBES · speech metrics | Context Relevance: 3.859 -> 4.584 | Improved |
| use unified multi-task model for talking-head synthesis | ViBES · TFHP | FDD: 20.77 -> 6.05 | Improved |
| use unified multi-task model for talking-head synthesis | ViBES · TFHP | LVE: 11.01 -> 10.87 | Improved |
| use ViBES for co-speech gesture generation on BEATv2 | ViBES · BEATv2 | FGD: 5.301 -> 5.257 | Improved |
| use ViBES for co-speech gesture generation on BEATv2 | ViBES · BEATv2 | Diversity: 15.167 -> 13.028 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MotionGPT — MotionGPT: Human Motion as a Foreign Language (NeurIPS 2023) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs (ICLR 2025 · similarity 0.89)
- INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations (CVPR 2025 · similarity 0.88)
- The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion (CVPR 2025 · similarity 0.88)
- U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation (CVPR 2026 · similarity 0.87)
- Digital Life Project: Autonomous 3D Characters with Social Intelligence (CVPR 2024 · similarity 0.87)
- $\tau$-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains (ICML 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
