Metraipolis › archive › dc_75dddae8382b
WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding — arXiv:2610.19419
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19419
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T21:55:57.972Z
- SHA-256 of the archived text
cc96bfd888e88a81d155ecc0b456e3bc3d56dd5b8701e4ae34bed98a2b1df5ac- Stable URL of this page
https://metraipolis.com/documento/dc_75dddae8382b
How to cite
WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding — arXiv:2610.19419 — arXiv (en), https://arxiv.org/abs/2610.19419 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75dddae8382b (Metraipolis archive dc_75dddae8382b, sha256 cc96bfd888e88a81d155ecc0b456e3bc3d56dd5b8701e4ae34bed98a2b1df5ac)
BibTeX
@misc{dc75dddae8382b,
title = {WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding — arXiv:2610.19419},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19419},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75dddae8382b; sha256 cc96bfd888e88a81d155ecc0b456e3bc3d56dd5b8701e4ae34bed98a2b1df5ac},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19419. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
MLLM-based detectors formulate vision-language grounding as autoregressive coordinate generation, yet in dense scenes, they often collapse into a box repetition loop, repeatedly emitting identical boxes until the decoding budget is exhausted. We trace this failure to historical-answer attention takeover: Under full-history autoregression, repeated coordinate tokens in the growing answer history attract disproportionate attention, crowding out the attention sinks needed to attend to new visual evidence. % To break this loop, in this paper, we propose \textbf{Compressed Window Auto-Regression} (WinAR). This new mechanism partitions a long answer sequence into consecutive generation windows and restricts full token-level autoregression to the current window only while compressing each previous window into a fixed set of latent tokens that condition subsequent decoding. This design reduces the repeated exposure to raw historical coordinates that triggers the attention takeover, yet preserves cross-window dependencies essential for coherent multi-object generation. On RSDense, which contains 200-2,000 objects per image, our model WinARDet improves RexOmni F1-score (IoU=0.5) from 32.16 to 39.36 over the baseline, while reducing the redundancy rate from 35.48% to 13.00%. WinARDet also generalizes across decoding strategies and output formats, including parallel box decoding and polygon generation, providing a practical paradigm for long-horizon vision-language grounding across scene densities.
Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.19419 — 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 2026-10-15T21:38:29.461Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).