LA-LoRA decouples LoRA matrix updates in DPFL settings to improve robustness to privacy noise, delivering up to 16.83% higher accuracy than prior LoRA variants on Swin-B under strict epsilon=1.
Fastpillars: A deployment-friendly pillar-based 3d detector
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
FALO achieves competitive accuracy on nuScenes and Waymo LiDAR benchmarks while running 1.6-9.8x faster than prior state-of-the-art methods on mobile GPUs and NPUs through a hardware-friendly voxel sequencing and ConvDotMix architecture.
Recent LiDAR 3D detectors remain as vulnerable to adversarial attacks as predecessors, with voxel-based and non-anchor-based models showing greater susceptibility under a multi-factor robustness framework.
citing papers explorer
-
Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models
LA-LoRA decouples LoRA matrix updates in DPFL settings to improve robustness to privacy noise, delivering up to 16.83% higher accuracy than prior LoRA variants on Swin-B under strict epsilon=1.
-
FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devices
FALO achieves competitive accuracy on nuScenes and Waymo LiDAR benchmarks while running 1.6-9.8x faster than prior state-of-the-art methods on mobile GPUs and NPUs through a hardware-friendly voxel sequencing and ConvDotMix architecture.
-
Comprehensive Robustness Analysis of LiDAR-based 3D Object Detection in Autonomous Driving
Recent LiDAR 3D detectors remain as vulnerable to adversarial attacks as predecessors, with voxel-based and non-anchor-based models showing greater susceptibility under a multi-factor robustness framework.