Related papers: Sensor Calibration Model Balancing Accuracy, Real-…
Recent advances in deep learning have significantly improved predictive accuracy. However, modern neural networks remain systematically overconfident, posing risks for deployment in safety-critical scenarios. Current post-hoc calibration…
Most current Deep Learning-based Semantic Communication (DeepSC) systems are designed and trained exclusively for particular single-channel conditions, which restricts their adaptability and overall bandwidth utilization. To address this,…
Sparse autoencoders (SAEs) are useful for detecting and steering interpretable features in neural networks, with particular potential for understanding complex multimodal representations. Given their ability to uncover interpretable…
Recently Transformers have provided state-of-the-art performance in sparse matching, crucial to realize high-performance 3D vision applications. Yet, these Transformers lack efficiency due to the quadratic computational complexity of their…
Sensor calibration usually is a time consuming yet important task. While classical approaches are sensor-specific and often need calibration targets as well as a widely overlapping field of view (FOV), within this work, a cooperative…
We demonstrate a novel architecture for Adaptive Optics (AO) control based on FPGAs (Field Programmable Gate Arrays), making active use of their configurable parallel processing capability. SPARC's unique capabilities are demonstrated…
We present Warp, a hardware platform to support research in approximate computing, sensor energy optimization, and energy-scavenged systems. Warp incorporates 11 state-of-the-art sensor integrated circuits, computation, and an…
Test-time adaptation (TTA) may fail to improve or even harm the model performance when test data have: 1) mixed distribution shifts, 2) small batch sizes, 3) online imbalanced label distribution shifts. This is often a key obstacle…
Two major challenges of 3D LiDAR Panoptic Segmentation (PS) are that point clouds of an object are surface-aggregated and thus hard to model the long-range dependency especially for large instances, and that objects are too close to…
We develop and implement in this paper a fast sparse assembly algorithm, the fundamental operation which creates a compressed matrix from raw index data. Since it is often a quite demanding and sometimes critical operation, it is of…
With information from multiple input modalities, sensor fusion-based algorithms usually out-perform their single-modality counterparts in robotics. Camera and LIDAR, with complementary semantic and depth information, are the typical choices…
Decentralized training enables learning with distributed datasets generated at different locations without relying on a central server. In realistic scenarios, the data distribution across these sparsely connected learning agents can be…
Robotic systems are typically composed of various subsystems, such as localization and navigation, each encompassing numerous configurable components (e.g., selecting different planning algorithms). Once an algorithm has been selected for a…
A compressed sensing method consists of a rectangular measurement matrix, $M \in \mathbbm{R}^{m \times N}$ with $m \ll N$, together with an associated recovery algorithm, $\mathcal{A}: \mathbbm{R}^m \rightarrow \mathbbm{R}^N$. Compressed…
In this paper, we investigate power-constrained sensing matrix design in a sparse Gaussian linear dimensionality reduction framework. Our study is carried out in a single--terminal setup as well as in a multi--terminal setup consisting of…
Accurate state-of-charge (SOC) estimation is essential for optimizing battery performance, ensuring safety, and maximizing economic value. Conventional current and voltage measurements, however, have inherent limitations in fully inferring…
Safety-critical 3D scene understanding tasks necessitate not only accurate but also confident predictions from 3D perception models. This study introduces Calib3D, a pioneering effort to benchmark and scrutinize the reliability of 3D scene…
Spiking Neural Networks (SNNs), as a biologically plausible alternative to Artificial Neural Networks (ANNs), have demonstrated advantages in terms of energy efficiency, temporal processing, and biological plausibility. However, SNNs are…
Sampled-data (SD) systems, which are composed of both discrete- and continuous-time components, are arguably one of the most common classes of cyberphysical systems in practice; most modern controllers are implemented on digital platforms…
Sparse arrays have emerged as a popular alternative to the conventional uniform linear array (ULA) due to the enhanced degrees of freedom (DOF) and superior resolution offered by them. In the passive setting, these advantages are realized…