Ahmed Mohamed

Ahmed Mohamed, Ahmed Aboulfotouh, Hatem Abou-Zeid

Wireless foundation models have emerged as a promising alternative to building separate models for each wireless task. However, existing approaches rely on masked input reconstruction, which can bias representations toward low-level signal details. In this paper, we propose LatentWave, a wireless foundation model pretrained using a Joint-Embedding Predictive Architecture (JEPA) on diverse wireless spectrograms and channel state information (CSI). By predicting masked regions in latent space, LatentWave learns representations that are more transferable out of the box across diverse downstream tasks. The proposed architecture employs per-channel patch embeddings with stochastic channel sampling during pretraining, allowing it to process variable antenna counts and improving usability across heterogeneous wireless configurations. We evaluate LatentWave on four downstream tasks: RF signal classification, 5G NR positioning, beam prediction, and LoS/NLoS classification, comparing against a masked-modeling baseline (WavesFM) pretrained on the same data. Additionally, we show that the masking geometry introduces a task-dependent inductive bias: frequency masking strongly favors channel-related tasks such as positioning and beam prediction, while region masking better preserves discriminability for signal classification.

Roberto Rojas-Cessa, Chuan-Kuo Wong, Zhengqi Jiang et al.

We propose the design and electrical description of an energy packet switch for forwarding and delivery of energy in digital power grids in this paper. The proposed switch may receive energy from one or multiple power sources in the form of energy packets, store them and aggregate the contained energy, and forward the accumulated energy to requesting loads connected to one or multiple output ports of the switch. Energy packets are discrete amounts of energy that are associated in- or out-of-band with an address and other metadata. Loads receive these discrete amounts of finely-controlled energy rather than discretionary amounts after. The control and management of the proposed switch are based on a request-grant protocol. Using energy packets helps to manage the delivery of power in a reliable, robust, and function form that may enable features not yet available in the present power grid. The switch, as any element of a digital grid, uses a data network for the transmission of these requests and grants. The energy packet switch may be the centerpiece for creating infrastructure in the realization of the digital power grid. The design of the energy packet switch is based on shared supercapacitors to shape and manage discretization of energy. We introduce the design and analysis of the electrical properties of the proposed switch and describe the procedure used in the switch to determine the amount of energy transmitted to requesting loads.

Yitong Tseo, M. I. Salkola, Ahmed Mohamed et al.

Clinical trials predicate subject eligibility on a diversity of criteria ranging from patient demographics to food allergies. Trials post their requirements as semantically complex, unstructured free-text. Formalizing trial criteria to a computer-interpretable syntax would facilitate eligibility determination. In this paper, we investigate an information extraction (IE) approach for grounding criteria from trials in ClinicalTrials(dot)gov to a shared knowledge base. We frame the problem as a novel knowledge base population task, and implement a solution combining machine learning and context free grammar. To our knowledge, this work is the first criteria extraction system to apply attention-based conditional random field architecture for named entity recognition (NER), and word2vec embedding clustering for named entity linking (NEL). We release the resources and core components of our system on GitHub at https://github.com/facebookresearch/Clinical-Trial-Parser. Finally, we report our per module and end to end performances; we conclude that our system is competitive with Criteria2Query, which we view as the current state-of-the-art in criteria extraction.

Ahmed Mohamed, Mostafa Ali, Shahd Ahmed et al.

Student disengagement in online learning has become a critical challenge, particularly post-pandemic. This review explores deep learning techniques used to detect disengagement, emphasizing computer vision and affective computing as effective approaches. We examine recent studies focusing on facial expressions, eye movements, and posture to assess student attention, along with non-face-based indicators like mouse activity. A systematic review of 38 selected studies outlines the indicators, methods, and models employed in this field, providing insights for future research on real-time engagement monitoring in online classrooms

Danilo Ribeiro, Omid Abdar, Jack Goetz et al.

Frame semantic parsing is an important component of task-oriented dialogue systems. Current models rely on a significant amount training data to successfully identify the intent and slots in the user's input utterance. This creates a significant barrier for adding new domains to virtual assistant capabilities, as creation of this data requires highly specialized NLP expertise. In this work we propose OpenFSP, a framework that allows for easy creation of new domains from a handful of simple labels that can be generated without specific NLP knowledge. Our approach relies on creating a small, but expressive, set of domain agnostic slot types that enables easy annotation of new domains. Given such annotation, a matching algorithm relying on sentence encoders predicts the intent and slots for domains defined by end-users. Extensive experiments on the TopV2 dataset shows that our model outperforms strong baselines in this simple labels setting.