Metraipolis › archive › dc_50dfbf5d4608
StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs — arXiv:2608.13416
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13416
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:55:55.045Z
- SHA-256 of the archived text
4cafb0c8cb8140a26017dc019472c79aad36b5529129cf1e9bea5330ebd9cc68- Stable URL of this page
https://metraipolis.com/documento/dc_50dfbf5d4608
How to cite
StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs — arXiv:2608.13416 — arXiv (en), https://arxiv.org/abs/2608.13416 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_50dfbf5d4608 (Metraipolis archive dc_50dfbf5d4608, sha256 4cafb0c8cb8140a26017dc019472c79aad36b5529129cf1e9bea5330ebd9cc68)
BibTeX
@misc{dc50dfbf5d4608,
title = {StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs — arXiv:2608.13416},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13416},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_50dfbf5d4608; sha256 4cafb0c8cb8140a26017dc019472c79aad36b5529129cf1e9bea5330ebd9cc68},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13416. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Humans effortlessly perceive the present while remembering the past, yet streaming VLMs often trade off real-time perception against long-term memory. Prior work shows that shortening the context can sharpen current-scene perception at the expense of long-range recall. To reconcile these abilities, we introduce StreamTTT, which writes long-range history into online-updated fast weights outside the attention context. This leaves a short sliding key-value cache dedicated to recent evidence, mitigating attention dilution. We train StreamTTT jointly on offline long-video QA and a newly constructed real-time QA corpus. On OVO-Bench, under each model's reported input protocol, StreamTTT-4B outperforms the same-scale SimpleStream-4B by 0.6 points in real-time perception and 5.3 points in backward tracing. It also surpasses the larger SimpleStream-8B by 0.73 points on StreamingBench's Real-Time Visual Understanding (RTVU) subset. Our code is publicly available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.13416 — 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 2026-10-19T04:46:30.245Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).