Metraipolis › archive › dc_c2e035d40da7
FRESHLATENT: Channel-Aware Latent Adaptation for Resource-Constrained Embodied VLM Perception — arXiv:2609.30629
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30629
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:04:55.659Z
- SHA-256 of the archived text
ef4f80254ebb834bd101f736666ef752e7070c53e63daf9b78763c6a89279bba- Stable URL of this page
https://metraipolis.com/documento/dc_c2e035d40da7
How to cite
FRESHLATENT: Channel-Aware Latent Adaptation for Resource-Constrained Embodied VLM Perception — arXiv:2609.30629 — arXiv (en), https://arxiv.org/abs/2609.30629 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2e035d40da7 (Metraipolis archive dc_c2e035d40da7, sha256 ef4f80254ebb834bd101f736666ef752e7070c53e63daf9b78763c6a89279bba)
BibTeX
@misc{dcc2e035d40da7,
title = {FRESHLATENT: Channel-Aware Latent Adaptation for Resource-Constrained Embodied VLM Perception — arXiv:2609.30629},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30629},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2e035d40da7; sha256 ef4f80254ebb834bd101f736666ef752e7070c53e63daf9b78763c6a89279bba},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30629. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Mission-critical UAVs increasingly rely on split vision-language model (VLM) perception under tight onboard-resource and wireless-communication constraints. However, corruption of transmitted intermediate features creates a deployment mismatch for clean-trained split interfaces, while stronger channel-aware codecs can impose substantial onboard cost. We present FreshLatent, a lightweight channel-aware latent adapter that trains a power-normalized encoder-decoder through wireless corruption while keeping the surrounding VLM frozen. We formulate deployment around a mission-conditioned perception requirement and embedded interface cost, linking channel quality and communication budget to the operating conditions under which perception remains usable. At 0 dB and the tightest communication budget, FreshLatent improves gIoU and cIoU over clean split compression by 20.79 and 20.87 points, respectively. At the most adverse evaluated SNR (0 dB), across all three communication budgets, FreshLatent recovers 63.5-69.1% of the gIoU improvement achieved by a much heavier, range-trained feature-JSCC codec. On an NVIDIA Jetson AGX Xavier in 10-W mode, FreshLatent uses 37-40x fewer encoder parameters, 7.7-9.9x lower edge-interface latency, and 8.8-10.0x lower edge-interface energy than the heavier codec. Together, these results show that lightweight channel-aware adaptation can recover a substantial fraction of the robustness of a much larger communication interface while broadening quality-valid operation under constrained wireless conditions. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-28 in cs.DC). Categorie arXiv: Signal Processing (eess.SP) ; Computer Vision and Pattern Recognition (cs.CV); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG); Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.30629 — 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 2026-10-08T01:40:22.300Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).