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

CREATORChengyu Qiao, Eryun Liu, Jingwei Ren, Long He
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE45 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13210932

Browse the full library · About the Tower of Babel