Proposes weakly supervised learning using foreground/background masks at 1% or 0.1% annotation rates
Explore technology by industry and role
Newest additions first. Explore past and current notes by industry and role.
All notes
Newest additions first. Explore past and current notes by industry and role.
Integrates real-world dynamic traffic scenarios into CARLA simulator through digital twin replication of actual intersections
A new event camera-based visual positioning system, EV-Pose, enables high-frequency, accurate 6-DoF pose estimation during drone landing.
ADPerf generates realistic point cloud data to expose increased latency in obstacle detection modules.
Nonlinear coupling enables minimum uncertainty through quantum squeezing, allowing full energy extraction from a bosonic quantum battery.
Introduces contrastive learning between visual feature networks and EEG large models to learn latent human driving cognition
A single unified architecture efficiently processes diverse sensor data using linear group RNNs.
Quantum advantage and stable energy storage achieved in quantum chaotic regime with n_b ≤ 4 under periodic delta-kick charging
RoboDriveBench, the first benchmark specifically designed to evaluate robustness of VLM-based autonomous driving systems, is introduced.
The RIC70115 gate driver integrates an internal LDO to provide stable 4.8V gate drive, ensuring consistent GaN performance under varying supply conditions.
A coordinated control framework integrating EVs, data centers, and BESS for fast frequency response
Extends existing Model-Based Parallelizer to support complex processing in autonomous driving software.
A numerical model is developed to simulate spacecraft-emitted electrons in solar plasma environments
Compresses early frame tokens into a few high-level tokens, reducing FLOPs by 66% while preserving performance
Photonic systems inherently embed probabilistic operations using physical entropy sources.