Diff-MomentFormer: Generative Diffusion-Augmented Transformer for End-to-End Joint Moment Estimation
Chengyu Qiao, Eryun Liu, Jingwei Ren, Long He · 2026
Read Diff-MomentFormer: Generative Diffusion-Augmented Transformer for End-to-End Joint Moment Estimation by Chengyu Qiao, Eryun Liu, Jingwei Ren, Long He (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13210932.txt.
Description
Chengyu Qiao and co-authors build a model that reads wearable sensors to estimate hip and knee joint torque. Their 2026 paper serves lower-limb exoskeletons, which need torque calls to help wearers move. Past end-to-end models stumble on long time links, thin data, and lopsided activity counts.
A diffusion model first fakes more training data, shaped by activity kind, with no class labels needed at run time. A transformer then reads the pooled sensor streams across long spans and mixed channels. On a public leg data set the pair lifts torque scores across activity kinds. Part-removal tests confirm each piece earns its place.
Catalog record
| CREATOR | Chengyu Qiao, Eryun Liu, Jingwei Ren, Long He |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |