arXiv cs.AI· Iago Brito, Walcy Rios, Lucas Fernandes, Kaiki de Oliveira, Arlindo Galv\~ao Filho·· 3 天前AI 评分24
共享隐空间为何未必兼容？Motion VAE 中的直接兼容性与可恢复对应关系
What Makes a Latent Space Shared? Direct and Recoverable Compatibility in Motion VAEs
AI 导读
在 HumanML3D 上的多 schema 运动 VAE 实验显示，即使输入完全相同，原始 Recall@1 仅为 5.9%–17.7%，配对 token 余弦相似度为 0.221–0.484，但经线性校准后对应关系几乎可完美恢复。
正文 · 原文
Abstract:A shared latent space is often assumed to make representations from different schemas directly interchangeable, yet sharing parameters, dimensionality, or a prior does not determine how corresponding instances are expressed in latent coordinates. We show that this assumption conflates recoverable correspondence, direct compatibility, and decoder reuse. In a controlled multi-schema motion VAE on HumanML3D, even identical inputs yield only $5.9$--$17.7\%$ raw Recall@1 and $0.221$--$0.484$ paired-token cosine, despite correspondence being almost perfectly recoverable after linear calibration. Cycle consistency strengthens recoverability but still leaves direct retrieval and token agreement near zero. In contrast, only $64$ paired clips raise raw Recall@1 to $88.4$--$90.3\%$ and token cosine to approximately $0.82$, making most post-hoc alignment unnecessary, although crossed decoding remains substantially worse than native reconstruction. We further find that reducing measured marginal discrepancy does not imply schema invariance. These results show that a shared backbone or prior does not ensure directly compatible latent coordinates, while limited paired correspondence can substantially improve direct compatibility in the tested setting.
| Subjects: | Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.17376 [cs.AI] |
| (or arXiv:2610.17376v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17376 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Iago Brito [view email]
[v1]
Mon, 12 Oct 2026 20:35:20 UTC (290 KB)
来源：arXiv cs.AI · arxiv.org