Metraipolis › archive › dc_caa2f69cd2ce

ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory — arXiv:2610.05097

Source: arXiv
Original: https://arxiv.org/abs/2610.05097
License (as archived): CC0-1.0
Archived: 2026-10-06T05:26:40.758Z
SHA-256 of the archived text: f97003b5465e7d3d1816be1679d207811d9181b19af3fe53c6bc613e049abcb7
Stable URL of this page: https://metraipolis.com/documento/dc_caa2f69cd2ce

How to cite

ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory — arXiv:2610.05097 — arXiv, https://arxiv.org/abs/2610.05097 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_caa2f69cd2ce (Metraipolis archive dc_caa2f69cd2ce, sha256 f97003b5465e7d3d1816be1679d207811d9181b19af3fe53c6bc613e049abcb7)

BibTeX

@misc{dccaa2f69cd2ce,
  title = {ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory — arXiv:2610.05097},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05097},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_caa2f69cd2ce; sha256 f97003b5465e7d3d1816be1679d207811d9181b19af3fe53c6bc613e049abcb7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05097. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As multimodal large language models (MLLMs) reason for longer, attention to the initial visual input diminishes, weakening visual grounding. Visual memory reintroduces visual evidence during reasoning. We conduct a controlled analysis of visual memory along three axes: curation, organization, and access. We find that local evidence benefits from global context, compact latent representations balance accuracy and visual-context cost, and the utility of memory access depends on the reasoning state. Guided by these findings, we propose ReMAP (Reasoning-Time Memory-Augmented Perception), which couples two complementary latent memories: a static, question-conditioned Global memory that preserves scene and cross-image context, and a dynamic Local memory that uses this context as an anchor while selecting and re-encoding region-level evidence according to the current reasoning state. Both memories return compact latent tokens inserted into the reasoning sequence, and a reinforcement-learning access policy trained with branched rollouts decides when to continue reasoning or invoke Global or Local memory. On ten benchmark families, ReMAP outperforms prior visual-memory methods on all four multi-image benchmarks, exceeding the strongest prior results on MuirBench and MIMIC by 8.38 and 14.84 percentage points. Across four backbone families, enabling memory access improves over the same trained model with memory disabled, and on shared V*Bench, CV-Bench-2D, and MuirBench questions ReMAP reduces the visual tokens entering the reasoning sequence by 51.0-76.8% relative to the native-resolution backbone. Further analyses show that Global and Local memory form distinct yet complementary latent representations. Together, these components restore the perceptual cycle by letting the reasoning state trigger targeted visual retrieval, with the retrieved evidence guiding subsequent reasoning.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.05097 — 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 2026-10-06T05:24:05.968Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).