pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Universal Skeleton Understanding via Differentiable Rendering and MLLMs

cs.CV · 2026-03-18 · unverdicted · novelty 6.0 · 3 refs

SkeletonLLM translates skeleton kinematics into compact image sequences via an end-to-end differentiable renderer DrAction and uses cooperative training to enable MLLMs to perform open-vocabulary action recognition, motion captioning, and QA across heterogeneous skeleton formats.

citing papers explorer

Showing 1 of 1 citing paper.

  • Universal Skeleton Understanding via Differentiable Rendering and MLLMs cs.CV · 2026-03-18 · unverdicted · none · ref 14 · 3 links

    SkeletonLLM translates skeleton kinematics into compact image sequences via an end-to-end differentiable renderer DrAction and uses cooperative training to enable MLLMs to perform open-vocabulary action recognition, motion captioning, and QA across heterogeneous skeleton formats.