Metraipolis › archive › dc_ce2ee6e64fd1

EgoTSR++: Egocentric Spatiotemporal Reasoning for Task Progress Understanding — arXiv:2609.31751

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31751
License (as archived)
CC0-1.0
Archived
2026-10-07T23:50:36.680Z
SHA-256 of the archived text
e3d92fa33a137248e00952f175786427385d1e435bdf8044b96df4ee5dea739a
Stable URL of this page
https://metraipolis.com/documento/dc_ce2ee6e64fd1

How to cite

EgoTSR++: Egocentric Spatiotemporal Reasoning for Task Progress Understanding — arXiv:2609.31751 — arXiv (en), https://arxiv.org/abs/2609.31751 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce2ee6e64fd1 (Metraipolis archive dc_ce2ee6e64fd1, sha256 e3d92fa33a137248e00952f175786427385d1e435bdf8044b96df4ee5dea739a)
BibTeX
@misc{dcce2ee6e64fd1,
  title = {EgoTSR++: Egocentric Spatiotemporal Reasoning for Task Progress Understanding — arXiv:2609.31751},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31751},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce2ee6e64fd1; sha256 e3d92fa33a137248e00952f175786427385d1e435bdf8044b96df4ee5dea739a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31751. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language Models (VLMs) have advanced rapidly in static visual understanding, yet remain unreliable when judging how an egocentric task is progressing. Given a task instruction and two visual observations, a model should determine which state is closer to the goal by analyzing task-relevant object configurations and spatial relations, rather than relying on timestamps or presentation order. This distinction is critical in manipulation, where retries, corrective actions, and temporary regressions make progress inherently non-monotonic. We introduce EgoTSR, a unified framework for diagnosing and improving order-robust task-progress understanding. First, SpatialLogic-Bench evaluates each physical state pair in both original and order-swapped presentations across short- and long-horizon settings, exposing whether a model follows task-state evidence or chronological shortcuts. Second, our data construction pipeline converts successful, approximately monotonic manipulation and first-person trajectories into bidirectional supervision; LongTag further preserves intermediate subtask structure for long-horizon comparison, while failure-aware data extend learning to regressions and recoveries. Third, a progressive CoT-to-Tag curriculum first supervises evidence-grounded interpretation of task-relevant state changes and then consolidates the comparison rule through scalable label-only training. Experiments reveal substantial input-order bias in representative VLMs. EgoTSR achieves 92.4% long-horizon accuracy with a 0.1-point forward-inverse Gap. Failure-aware supervision further improves accuracy on non-monotonic trajectories by 11.8 points and Recovery Accuracy by 11.2 points, while maintaining broad visual and spatial capabilities. These results establish goal-conditioned state comparison as an explicit formulation of egocentric spatiotemporal reasoning for task-progress understanding.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.31751 — 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 2026-10-07T23:29:26.927Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).