Metraipolis › archive › dc_8da1f43c8f45

TACD: Distilling Efficient Text-to-Motion Models via Terminal Amplification Control — arXiv:2610.02867

Source
arXiv
Original
https://arxiv.org/abs/2610.02867
License (as archived)
CC0-1.0
Archived
2026-10-05T22:49:19.633Z
SHA-256 of the archived text
6d0f2edb132d7eb17c9c07f4f5b508edbfde09b30077c06501b8150f7f3d0fb9
Stable URL of this page
https://metraipolis.com/documento/dc_8da1f43c8f45

How to cite

TACD: Distilling Efficient Text-to-Motion Models via Terminal Amplification Control — arXiv:2610.02867 — arXiv, https://arxiv.org/abs/2610.02867 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8da1f43c8f45 (Metraipolis archive dc_8da1f43c8f45, sha256 6d0f2edb132d7eb17c9c07f4f5b508edbfde09b30077c06501b8150f7f3d0fb9)
BibTeX
@misc{dc8da1f43c8f45,
  title = {TACD: Distilling Efficient Text-to-Motion Models via Terminal Amplification Control — arXiv:2610.02867},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02867},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8da1f43c8f45; sha256 6d0f2edb132d7eb17c9c07f4f5b508edbfde09b30077c06501b8150f7f3d0fb9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02867. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent text-to-motion models have improved motion quality and instruction following, yet many-step denoising and large model components make deployment slow and memory-intensive. We present Terminal-Amplification-Controlled Distillation (TACD), an on-policy approach for training efficient motion generators from text prompts and pretrained teachers, without real-motion training data. Building on segmented on-policy flow distillation, we supervise clean-motion predictions along student-generated trajectories. We identify a failure mode in which velocity matching on a fixed supervision grid repeatedly overweights errors near the denoising endpoint, degrading few-step generation. TACD ties the latest teacher query to the student's step size, bounding the effective loss weights in clean-motion space without changing inference. Experiments on HumanML3D and KIT-ML demonstrate improved few-step generation, including a 58% reduction in eight-step HY-Motion student FID relative to distillation without this bound. For diffusion teachers, the endpoint-matching form of TACD yields four-step students with lower FID and matched or improved text-motion retrieval relative to their 50-step teachers on HumanML3D. On HY-Motion and Kimodo, eight-step students with compact components achieve 7.7-11.9x end-to-end speedups and reduce peak GPU memory by 3.8-6.7x relative to their teachers. Project page: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.02867 — 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 2026-10-05T22:45:55.645Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).