arXiv:2606. 24483v1 Announce Type: cross Abstract: The deployment of unmanned aerial vehicles (UAV) as open radio units (O-RUs) in 6G cellular systems presents a promising opportunity to achieve scalable and adaptive network coverage.
arXiv:2606. 01325v1 Announce Type: cross Abstract: Unmanned Aerial Vehicles (UAVs) equipped with radar sensors are deployed for target search missions in diverse environments, where targets exhibit characteristic signatures (e.
The paper addresses lifelong aerial autonomy by treating visual place recognition (VPR) as a mission‑based domain‑incremental learning problem. It introduces a heterogeneous memory framework that first trains on a static satellite exemplar memory and then uses a bounded replay buffer to retain selected airborne observations across missions. The proposed DBS‑Hybrid replay strategy, which blends prototype‑based diversity trimming with representative‑first feature‑space coverage, outperforms baseline methods in accuracy, generalization, and knowledge retention across multiple UAV missions.
arXiv:2606. 05661v1 Announce Type: new Abstract: Continual learning, the ability of AI systems to improve through sequential experience, has attracted substantial interest, but no high-quality benchmark exists to evaluate it.
Changepoint-Aware World Models (CAWM) is a DreamerV3 agent that detects abrupt dynamics shifts in a robot’s environment using an online CUSUM test on internal prediction error. Upon detection, CAWM selectively forgets stale replay data while preserving the learned representation, enabling rapid recovery from shifts such as doubled gravity or halved actuator gain. Experiments on simulated locomotion show CAWM recovers faster than passive retraining and outperforms a baseline that respawns a fresh dynamics model, achieving significant return gains in the first 30k post‑shift frames.
arXiv:2610.08315v1 Announce Type: new Abstract: Counter-UAV systems based on thermal infrared detection must stay accurate as operational datasets evolve, yet sequential fine-tuning causes catastroph...
arXiv:2504. 13822v3 Announce Type: replace-cross Abstract: The emergence of large pre-trained networks has revolutionized the AI field, unlocking new possibilities and achieving unprecedented performance.
arXiv:2605. 25170v2 Announce Type: replace-cross Abstract: Training data for olfaction is scattered through disparate, non-standardized datasets that limit the ability to build representative world models.
The paper introduces AIR, an analytic imbalance rectifier designed for continual learning scenarios where data streams are evolving and imbalanced. AIR operates without exemplars, using a frozen backbone for feature extraction and a closed‑form incremental classifier that incorporates a class‑weighted ridge objective. It employs an analytic reweighting module to equalize sample weights across classes, achieving significant improvements in accuracy and macro F1 over 28 baseline methods in long‑tailed class‑incremental learning and over 15 baselines in the Si‑Blurry setting with recurring classes.
arXiv:2607. 07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn?
CoMemNet is a Continual Memory Network designed for traffic prediction on evolving sensor networks. It combines an online branch that adapts to current data with an exponential‑moving‑average target branch for stable reference, and uses a Wasserstein‑based drift sampler to selectively update drift‑sensitive nodes. A lightweight temporal memory replay buffer stores compact states, allowing efficient adaptation without traversing all historical data. Experiments on PeMS datasets show that CoMemNet maintains stable accuracy and outperforms retraining baselines in both prediction performance and training time.
arXiv:2609.36375v1 Announce Type: new Abstract: Continual learning is usually studied through mechanisms that preserve old knowledge. We develop Successional Learning Theory (SLT), a mesoscopic accou...