Metraipolis › archive › dc_83bceabae191
BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion — arXiv:2609.35407
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35407
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:54:45.953Z
- SHA-256 of the archived text
66803aad723a9676ef3cd725f2b9c612e9bdb1a5ea436411449cf4d411fce37a- Stable URL of this page
https://metraipolis.com/documento/dc_83bceabae191
How to cite
BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion — arXiv:2609.35407 — arXiv (en), https://arxiv.org/abs/2609.35407 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_83bceabae191 (Metraipolis archive dc_83bceabae191, sha256 66803aad723a9676ef3cd725f2b9c612e9bdb1a5ea436411449cf4d411fce37a)
BibTeX
@misc{dc83bceabae191,
title = {BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion — arXiv:2609.35407},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35407},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_83bceabae191; sha256 66803aad723a9676ef3cd725f2b9c612e9bdb1a5ea436411449cf4d411fce37a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35407. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Text-to-motion generation and motion-to-text captioning are two fundamental tasks in human motion modeling, both grounded in the same underlying motion-text correspondence. Existing unified approaches mostly rely on autoregressive modeling, which imposes a fixed generation order and is therefore poorly suited to the bidirectional dependencies between language and motion, allowing early prediction errors to persist as fixed context and degrade both temporal coherence and cross-modal consistency. Masked discrete diffusion, which models sequences through iterative bidirectional prediction, offers a natural remedy. We therefore propose BiMoGen (Bidirectional Motion-text Generation), a unified masked discrete diffusion framework for bidirectional motion-text modeling. To stabilize training, we design Decoupled Uni- and Cross-Modal Training, in which masked pretraining first establishes cross-modal correspondence on paired motion-text sequences, after which supervised fine-tuning specializes the model for bidirectional generation. Masked diffusion nonetheless introduces its own source of error, as the model is trained on clean ground-truth context yet encounters self-generated and potentially erroneous context at inference, with errors committed under heavily masked states propagating through subsequent steps. We further introduce Generation-Aware Self-Correction that exposes the model to its own predictions during training and applies correction passes at early sampling steps to revise unreliably committed tokens. Extensive experiments on HumanML3D and KIT-ML demonstrate competitive performance on both tasks, validating the effectiveness of the proposed two-stage training and self-correction designs. The project page is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.35407 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T23:29:27.565Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).