ESARBench is the first unified benchmark for MLLM-driven UAV agents that must explore, locate clues, and decide on victim positions in photorealistic simulated SAR environments.
Risk-Aware Shared Control for Teleoperation of Automated Vehicles in Dynamic Environments,
7 Pith papers cite this work, alongside 78 external citations. Polarity classification is still indexing.
7
Pith papers citing it
78
external citations · external index
citation-role summary
baseline 1
citation-polarity summary
years
2026 7roles
baseline 1polarities
baseline 1representative citing papers
ResAware improves cross-environment website fingerprinting robustness by distilling resource-privileged knowledge into a traffic-only student model, raising Var-CNN F1 from 72.77% to 81.49% under 150-day drift on a 160k-sample dataset.
A systematic review of on-device AI inference security finds defenses are imbalanced, with roughly half focused on IP theft while one-third of attacks (adversarial examples) lack any associated defenses.
SwitchBraidNet, a 3 KB neural network, reports ~69% motor-imagery and ~93% SSVEP accuracy after INT8 quantisation-aware training on OpenBMI.
Proposes basing teleoperation ODD on minimal risk maneuver capability with a dedicated system, demonstrated via use case.
Unsupervised domain adaptation with GSDE achieves ~80% accuracy in cross-process TIG-laser weld penetration prediction, improving supervised baselines by over 43%.
Energy features support 85-90% surface classification accuracy with DL models across three datasets and yield 1-2% gains when fused with inertial data.
citing papers explorer
-
ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue
ESARBench is the first unified benchmark for MLLM-driven UAV agents that must explore, locate clues, and decide on victim positions in photorealistic simulated SAR environments.
-
ResAware: Cross-Environment Website Fingerprinting via Resource-Privileged Distillation
ResAware improves cross-environment website fingerprinting robustness by distilling resource-privileged knowledge into a traffic-only student model, raising Var-CNN F1 from 72.77% to 81.49% under 150-day drift on a 160k-sample dataset.
-
Protecting On-Device AI Inference: A Systematic Review of Attacks and Defence Mechanisms
A systematic review of on-device AI inference security finds defenses are imbalanced, with roughly half focused on IP theft while one-third of attacks (adversarial examples) lack any associated defenses.
-
SwitchBraidNet: Quantisation-Aware Lightweight Architecture for Hybrid Brain-Computer Interface
SwitchBraidNet, a 3 KB neural network, reports ~69% motor-imagery and ~93% SSVEP accuracy after INT8 quantisation-aware training on OpenBMI.
-
Teleoperation Operational Design Domain based on Minimal Risk Maneuver Capability
Proposes basing teleoperation ODD on minimal risk maneuver capability with a dedicated system, demonstrated via use case.
-
A cross-process welding penetration status prediction algorithm based on unsupervised domain adaptation in laser and TIG welding
Unsupervised domain adaptation with GSDE achieves ~80% accuracy in cross-process TIG-laser weld penetration prediction, improving supervised baselines by over 43%.
-
Leveraging Energy Features for Surface Classification with Deep Learning: A Comparative Analysis Across Three Independent Datasets
Energy features support 85-90% surface classification accuracy with DL models across three datasets and yield 1-2% gains when fused with inertial data.