Metraipolis › archive › dc_20302b7c19e0

Remember Smarter: Visual History Compressor and Hyperbolic Experience Space for Robotic Memory — arXiv:2608.15269

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.15269
License (as archived): CC0-1.0
Archived: 2026-10-18T23:05:46.133Z
SHA-256 of the archived text: 2878aef30393ec5a8416587b20952a34f2e540d67bedc5a34db2a256b5961c92
Stable URL of this page: https://metraipolis.com/documento/dc_20302b7c19e0

How to cite

Remember Smarter: Visual History Compressor and Hyperbolic Experience Space for Robotic Memory — arXiv:2608.15269 — arXiv (en), https://arxiv.org/abs/2608.15269 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_20302b7c19e0 (Metraipolis archive dc_20302b7c19e0, sha256 2878aef30393ec5a8416587b20952a34f2e540d67bedc5a34db2a256b5961c92)

BibTeX

@misc{dc20302b7c19e0,
  title = {Remember Smarter: Visual History Compressor and Hyperbolic Experience Space for Robotic Memory — arXiv:2608.15269},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15269},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_20302b7c19e0; sha256 2878aef30393ec5a8416587b20952a34f2e540d67bedc5a34db2a256b5961c92},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15269. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-horizon robot policies require compact access to recent observations and reusable experience without expanding the vision-language-action (VLA) context. We introduce Remember Smarter (RS), a plug-and-play module with complementary visual-history and hyperbolic experience-memory branches. Its visual branch compresses multi-view patch histories using bidirectional spatial Mamba and causal temporal Mamba, then exposes the resulting memory to action-facing hidden states through residual cross-attention while leaving the VLM visual-token stream unchanged. Its experience branch stores successful final-layer VLM states in a Poincare VAE space, organizes them hierarchically, and asynchronously converts retrieved experience into geodesic prompt tokens without blocking action inference. When adapted to pi0, RS increases total success on LIBERO-Plus from 53.6% to 70.6% and achieves substantial performance gains in real-robot experiments designed to evaluate memory retention and experience utilization.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-18 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.15269 — 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 2026-10-18T23:01:50.349Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).