13 accepted papers
Learning from continuous-time trajectories requires modeling multivariate sensor measurements generated by underlying physical or dynamical processes. Under extreme data compression and heterogeneous sampling, directly optimizing synthetic signals as discrete sample values becomes fundamentally misa…
Conformal prediction (CP) and its extension, conformal risk control (CRC), are established frameworks for quantifying uncertainty in supervised machine learning through formal guarantees. However, recent breakthroughs in artificial intelligence (AI) have been driven by unsupervised generative models…
Sensory Temporal Action Detection (STAD) aims to localize and classify human actions within long, untrimmed sequences captured by non-visual sensors such as WiFi or inertial measurement units (IMUs). Unlike video-based TAD, STAD poses unique challenges due to the low-dimensional, noisy, and heteroge
Synthetic Aperture Radar (SAR) imagery plays a critical role in all-weather, day-and-night remote sensing applications. However, existing SAR-oriented deep learning is constrained by data scarcity, while the physically grounded speckle noise in SAR imagery further hampers fine-grained semantic repre
WiFi sensing offers passive and privacy-preserving perception that complements vision-based sensing, but its performance degrades sharply under domain shifts caused by changes in environment, subjects, or hardware. This challenge is exacerbated in real-world deployments where source data are unavail
Performance of current point cloud-based outdoor 3D object detection relies heavily on large-scale high-quality 3D annotations. However, such annotations are usually expensive to collect and outdoor scenes easily accumulate massive unlabeled data containing rich scenes. Semi-supervised learning is a
In this paper, we present non-asymptotic optimization guarantees of gradient descent methods for estimating structured transition matrices in high-dimensional vector autoregressive (VAR) models. We adopt the projected gradient descent (PGD) for single-structured transition matrices and the alternati…
Training and inference efficiency of deep neural networks highly rely on the performance of tensor operators on hardware platforms. Manually optimizing tensor operators has limitations in terms of supporting new operators or hardware platforms. Therefore, automatically optimizing device code configu…
This work proposes a novel and scalable reinforcement learning approach for routing in ad-hoc wireless networks. In most previous reinforcement learning based routing methods, the links in the network are assumed to be fixed, and a different agent is trained for each transmission node — this limits…
Recognition of human activities is an important task due to its far-reaching applications such as healthcare system, context-aware applications, and security monitoring. Recently, WiFi based human activity recognition (HAR) is becoming ubiquitous due to its non-invasiveness. Existing WiFi-based HAR…
A wireless sensing system with n sensors, observing independent and identically distributed continuous random variables with a symmetric probability density function, and one non-collocated estimator acting as a fusion center is considered. The sensors transmit information to the fusion center via a…
Robust optimization is an important task in wireless communications, because due to fading and feedback delay there is inherent uncertainty in channel state information in a wireless environment. This paper aims to show that a deep learning approach for network utility maximization can produce more…
To reach a higher number of degrees of freedom by exploiting the fourth-order difference co-array concept, an effective structure extension based on two-level nested arrays is proposed. It increases the number of consecutive lags in the fourth-order difference coarray, and a virtual uniform linear a…