Signal Processing

Haohe Liu, Xuenan Xu, Yi Yuan et al.

This work addresses the need for efficient, low-bitrate audio compression with rich semantic clues for applications in audio processing and language modeling, representing a novel advancement rather than an incremental improvement.

Che Liu, Zhongwei Wan, Cheng Ouyang et al.

This work addresses the limitation of requiring annotated data for ECG classification in clinical practice, offering a zero-shot approach that could reduce reliance on costly expert labeling.

Yuezhou Ma, Haixu Wu, Hang Zhou et al.

This addresses the suboptimal practice in physics sensing where reconstruction and sensor placement are not mutually enhanced, benefiting scientific and engineering domains that rely on accurate sensor data.

Sion An, Myeongkyun Kang, Soopil Kim et al.

This addresses the problem of inter-subject variability in EEG-based brain-computer interfaces, offering a more practical alternative to time-consuming task-specific signal recording.

Yuexi Du, Jiazhen Zhang, Nicha C. Dvornek et al.

This work addresses the problem of designing efficient and robust rotation/reflection equivariant networks for computer vision applications, representing a novel method rather than an incremental improvement.

Ming Lei, Christophe Baehr

This work addresses fundamental challenges in geometric deep learning by unifying knowledge representation with quantum entanglement concepts, though it appears to be a novel paradigm rather than incremental.

Qinfan Xiao, Ziyun Cui, Chi Zhang et al.

This addresses the challenge of unifying diverse brain signal data for researchers in neuroscience and medical diagnostics, though it is incremental as it builds on foundation model concepts applied to a new domain.

Shida Jiang, Junzhe Shi, Scott Moura

This addresses a foundational issue in state estimation for nonlinear systems, which is critical for applications like robotics and control, though it is incremental as it builds on existing nonlinear Kalman filter methods.

Wei-Bang Jiang, Xi Fu, Yi Ding et al.

This addresses the challenge of robust multimodal analysis in healthcare and brain-computer interfaces, offering a novel foundation model approach.

Hans van Gorp, Davide Belli, Amir Jalalirad et al.

This work addresses improved positioning accuracy for GNSS users in challenging urban scenarios, representing a novel deep learning-based integration approach.

Yiping Meng, Yiming Sun

This addresses the need for personalized health interventions in built environments, representing a new paradigm rather than an incremental improvement.

Feiyang Pan, Shenghe Zheng, Chunyan Yin et al.

This addresses a critical problem in inertial navigation and motion control by providing a scalable software solution to overcome hardware limitations.

Ruud JG van Sloun

This addresses unreliable ultrasound diagnosis in difficult-to-image patients by making systems more autonomous and adaptive.

Arvind Pillai, Dimitris Spathis, Fahim Kawsar et al. · cambridge

This work addresses the need for robust, generalizable models in optical physiological signal monitoring for cardiovascular health and other applications, representing a significant advance rather than an incremental improvement.

Kyriakos Stylianopoulos, Paolo Di Lorenzo, George C. Alexandropoulos

This work addresses energy efficiency in edge inference for wireless systems, representing a novel paradigm shift in goal-oriented communications.

Jingwen Tong, Zijian Li, Fang Liu et al.

This addresses the labor-intensive and suboptimal process of building AI agents for wireless tasks, offering a scalable solution for researchers and practitioners in wireless networking.

Xuyang Li, Hamed Bolandi, Mahdi Masmoudi et al.

This addresses the problem of scalable and low-cost structural health monitoring for civil infrastructure, offering a deploy-and-forget solution that reduces human intervention and inspection costs.

Shuhao Ma, Jie Zhang, Chaoyang Shi et al.

This addresses the challenge of high computational latency in physics-based models and the need for labeled data in data-driven methods for biomechanical analysis, offering a more practical solution for researchers and clinicians.

Adam Watts, Andrew Jeon, Destry Newton et al.

This work addresses a problem for engineers and researchers working with single-degree-of-freedom systems, providing a more efficient and scalable approach to inverse shock response spectrum reconstruction.

Chunyu Liu, Hao Zhang, Wei Wu et al.

This work addresses spectrum efficiency and security for wireless communication systems, representing a new paradigm rather than an incremental improvement.