arXiv:2608. 14670v1 Announce Type: cross Abstract: Passive, device-free person identification offers an alternative to camera- and wearable-based biometrics, yet existing wireless approaches rely largely on gait or activity cues and are rarely evaluated at scale.
By Nayan Sanjay Bhatia, Pranay Kocheta, Yuhan Li, Katia Obraczka
CSI-JEPA is a self‑supervised framework that learns reusable temporal‑spectral representations from unlabeled Wi‑Fi channel state information (CSI) by predicting latent features of masked channel regions. It tokenizes CSI along time and subcarrier dimensions and uses a channel‑variation‑aware masking strategy to focus on dynamic regions. After pretraining, the frozen encoder is adapted with lightweight adapters to a variety of downstream Wi‑Fi sensing tasks, achieving significant accuracy gains and label savings compared to supervised baselines.
By Xuanhao Luo, Zhizhen Li, Yuchen Liu
arXiv:2606. 31495v1 Announce Type: new Abstract: We study a single idea across two settings: that a prediction-error signal, computed by a small predictor over the latent space of a frozen encoder, can serve both as a gate on plasticity and as a substrate for metacognition.
By Louis Mouchon
arXiv:2606. 29465v1 Announce Type: new Abstract: Class-incremental learning requires a model to learn new classes while preserving decision regions for old ones.
By Weizhi Nie, Hui Wang, Weijie Wang, Yuting Su
The paper proposes a drift‑adaptive method for Domain‑Incremental Learning that tracks representation drift for each past domain‑class pair. By measuring how much a concept’s current representation deviates from a fixed anchor, the method assigns stronger preservation to high‑drift pairs and down‑weights highly drifted domains during prototype construction. Experiments on DomainNet, Office‑Home, CORe50, and CDDB‑Hard show that this approach maintains a strong accuracy‑forgetting balance while using less training memory and the smallest storage compared to other methods.
By Hyunmin Kong, Gyutae Oh, Jitae Shin
arXiv:2606. 03939v1 Announce Type: cross Abstract: Federated Learning (FL) of foundation and edge models increasingly targets deployments where client data distributions drift over time, yet existing forgetting-mitigation methods assume each client's distribution is stationary.
By Mubarak A. Ojewale, Adriana E. Chis, Jorge M. Cortes-Mendoza, Bernardo Pulido-Gaytan, Horacio Gonzalez-Velez