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.
Figures & tables
Figure 1: Motivation for FreshLatent . (a) Mission-driven UAVs rely on query-conditioned semantic perception. (b) Onboard resource constraints motivate UAV–server split VLM execution. (c) Split inference couples onboard interface cost, communication budget, and wireless channel quality. (d) Channel corruption can degrade downstream perception and render the returned evidence insufficient for the required task quality, motivating channel-aware latent adaptation.
Figure 2: Overview of FreshLatent in the split LISA pipeline. The UAV extracts an intermediate SAM feature F and transmits a compressed latent z over the wireless link. The server reconstructs F~ , which is consumed together with the operator query by the frozen downstream LISA pipeline. FreshLatent adapts only the communication interface spanning 4 – 6 ; the surrounding perception pipeline remains unchanged.
Figure 3: Reasoning-segmentation quality under matched communication budgets. Columns correspond to K=0.262 , 0.524 , and 1.311×106 channel uses per image; the upper and lower rows report gIoU and cIoU [ 13 ] , respectively. HEVC fails to decode below 13 dB (gIoU 0.06 , cIoU 0.12 ), so its curve drops below the plotted range. FreshLatent improves gIoU and cIoU over Clean by 20.79 and 20.87 points at 0 dB and K=0.262 M.
Figure 4: Fraction of the 27 evaluated (K,γ) points satisfying selected gIoU requirements τμ . FL-Fixed and SNR-Specialist are omitted because they serve as an ablation and condition-specific reference, respectively. HEVC is omitted because decoding fails below 13 dB, making its coverage dominated by decoder availability rather than the quality requirement. FreshLatent increases quality-valid coverage over Clean by 3.7–11.1 percentage points across all shown requirements.