Clay weekly context brief for the Systems category (ISO week 2026-W41). Clay tracks publications from the Systems feed list. Below are recent items from this category, each with its source and a short description of what the publication covers when one is available in the source feed. Recent publications: 1. Everywhere Learning: Artificial Intelligence with Pointwise Constraints Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2606.01557 Everywhere learning is a new paradigm whereby Artificial Intelligence (AI) systems are trained to satisfy loss constraints with probability one over the data distribution. 2. What Should World Models Forget? Stratified Retention for Continual Adaptation Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2610.03713 Continual learning treats degradation on previously seen data as evidence of failure, a convention inherited from settings with a stationary prediction target, where a correct label remains correct indefinitely. 3. Controllable Accent Normalization via Discrete Diffusion Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2603.14275 Existing accent normalization methods do not typically offer control over accent strength, yet many applications-such as language learning and dubbing-require tunable accent retention. 4. Encoding and Decoding Temporal Signals with Spiking Bandpass Wavelets Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2605.09770 Spike-based encodings are sparse and energy-efficient. 5. FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized Adapters Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2610.02799 Fisheye cameras give mobile robots a single-sensor, low-cost view of their surroundings, yet the COCO-pretrained detectors that practitioners routinely reuse fail on them: strong radial distortion warps local image structure, while boundary compression shrinks objects to near-invisible sizes. 6. Effects of interpulse-interval variation on deep-learning classification of bat vocalizations Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2610.02284 Temporal context may aid automated bat-species classification, but the contribution of specific features remains unclear. 7. Infinity Search: Approximate Vector Search with Projections on q-Metric Spaces Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2506.06557 An ultrametric space or infinity-metric space is defined by a dissimilarity function that satisfies a strong triangle inequality in which every side of a triangle is not larger than the larger of the other two. 8. Wrong Organ, Right Physics: Transferring Echocardiography Pretraining to Lung Ultrasound for Tuberculosis Screening Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2610.03290 Lung ultrasound (LUS) is attractive for tuberculosis (TB) screening at primary-care level, but labelled cohorts are small. 9. Multiclass Speech Classification Under Noise Disparity Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2610.03381 We investigate noise disparity in multi-class speech classification tasks and develop a strategy to prevent classifiers from exploiting class-dependent noise characteristics. 10. Distributed Power Control for Equal-Priority NGSO Mega-Constellation Coexistence Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2609.38935 Two non-geostationary orbit (NGSO) mega-constellations over shared spectrum leads to inter-constellation interference. 11. One Photon, Many Worlds: Posteriors and Predictions with Single-Photon Cameras Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2610.02675 Single-photon avalanche diode (SPAD) cameras operate fundamentally differently from conventional cameras due to their photon-counting nature. 12. Augmenting Large Audio Language Models with Low-Level Acoustic Features for Dysarthric Speech Detection Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2610.03352 Automatic dysarthric speech detection approaches can support traditional clinical diagnosis, which relies on costly and time-consuming evaluation by a speech and language pathologist. 13. Reconfigurable Intelligent Surfaces for 6G and Beyond: A Comprehensive Survey from Theory to Deployment Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2506.19526 As the wireless research community moves toward shaping the vision of sixth-generation (6G) networks, reconfigurable intelligent surfaces (RIS) have emerged as a promising technology for controlling the propagation environment. 14. Reliability Stress Tests and Decision-Time Routing for Chest X-ray Vision-Language Models Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2610.02270 Medical vision-language model (VLM) evaluation is sensitive to workflow design, prompting strategy, and benchmark construction, yet most studies treat these factors in isolation. 15. CoLMbo-SV: A Grounded Language Model for Explainable Speaker Verification Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2609.33212 Speaker verification systems achieve high accuracy but provide little account of the acoustic evidence behind their judgments. 16. Outage Probability Analysis of Tunable Liquid Lens-assisted VLC Systems Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2505.14236 This paper presents a tunable liquid lens (TLL)-assisted indoor mobile visible light communication system. 17. Confidence-Gated Cloud-Edge Cascade Triage via Variational Risk Minimization for Medical Imaging Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2610.02269 Emergency chest X-ray (CXR) triage has a structural modality gap: reports arrive after triage decisions, yet multimodal foundation models require image-text inputs. Sources in this brief: eess.AS (Audio and Speech Processing); eess.IV (Image and Video Processing); eess.SP (Signal Processing). Selected 17 of 33 available items for this weekly brief.