Locating and Repairing Domain Shift in VLM Trajectory Planning
Overview
This research introduces MoLaRx (Modality-Layer Repair), a framework designed to address domain shift in Vision-Language Model (VLM) trajectory planners.
Generated from attributed reports · Updated 4 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · inference latency reduction: 8.4 other · Basis not reported
“mong adaptation methods in all six main-table settings, while using 50-60% fewer trainable parameters and 8.4-10.9 ms lower inference latency. In contrast, uniform MMD-only adaptation collapses in all six settings, highlighting the importance of structure-guided repair.”
Exact source · revision 1Source owner not reported
Reported quantity · cross-city benchmarks evaluated: 2 other · reported trials
“R) then applies a matched operator (Maximum Mean Discrepancy (MMD) / low-rank adaptation (LoRA) / freezing) to repair each zone, with the composition adapting automatically to each architecture. We evaluate MoLaRx on three architecturally distinct VLMs (LFM2-VL-1.6B, Qwen2-VL-2B, and PaliGemma2-3B) across two cross-city benchmarks (nuScenes and Argoverse 2). MoLaRx attains the lowest cross-city trajectory-error gap a”
Exact source · revision 1Source owner not reported
Reported quantity · main-table settings: 6 other · reported trials
“mong adaptation methods in all six main-table settings, while using 50-60% fewer trainable parameters and 8.4-10.9 ms lower inference latency. In contrast, uniform MMD-only adaptation collapses in all six settings, highlighting the importance of structure-guided repair.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalLocating and Repairing Domain Shift in VLM Trajectory Planning
This research introduces MoLaRx (Modality-Layer Repair), a framework designed to address domain shift in Vision-Language Model (VLM) trajectory planners.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).