aiqbench analysis
FreshLatent introduces a lightweight adapter that enables split vision-language models to maintain robust perception in UAVs despite wireless channel corruption, significantly reducing edge latency and energy consumption compared to heavier codecs. By keeping the main VLM frozen while training only the interface components, this approach offers a practical solution for deploying resource-constrained AI systems in mission-critical robotic scenarios.
FRESHLATENT: Channel-Aware Latent Adaptation for Resource-Constrained Embodied VLM Perception
arXiv:2609.30629v1 Announce Type: cross Abstract: 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.
Abstract: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.
Paper is currently under review. Authors' version posted for personal use and not for redistribution
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)
arXiv:2609.30629 [eess.SP]
(or arXiv:2609.30629v1 [eess.SP] for this version)
https://doi.org/10.48550/arXiv.2609.30629 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 247 words
Related coverage
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · Sep 17, 2026
NARRAS: Edge-Triggered Distributed Inference for CSI-Based Localization in Vehicular IoT Networks
arXiv · Jun 12, 2026
FASA: Feedback-Aware Sampling Adaptation for Efficient Diffusion-Based VLA Models
arXiv · Sep 18, 2026
FedSAP: Federated Learning with Structured Adaptive Partitioning for Multi-Domain Heterogeneous Edge Devices
arXiv · Oct 2, 2026