Clay weekly context brief for the Systems category (ISO week 2026-W44).

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. GateFormer: Forecast-Space Decomposition for Intra-Hour Solar Irradiance Prediction from Sky Images
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.30942
   Sub-hourly dispatch, balancing, and storage control increasingly depend on forecasts that anticipate rapid variability in solar generation.
2. Lip-Focused Audio-Visual Consistency Detects Speech Content Manipulation beyond Coarse Synchronization
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2610.30872
   Speech-content manipulation changes what a visible person appears to say by replacing the speech track and, in stronger attacks, regenerating mouth motion to match the forged utterance.
3. Damage detection in railway wheels from impact-induced ultrasonic ring-down using self-referenced decay features
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.30541
   This study evaluates a non-contact screening method for stationary railroad wheelsets using air-coupled ultrasonic measurements excited by hammer impacts.
4. A Contrastive Learning Framework for Label-Efficient Gastric Cancer Detection and Intra-Tumour Progression Analysis
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.30316
   Gastric Cancer is among the leading causes of cancer-related mortality worldwide.
5. Hear Every Sound Object: Rescuing Overlooked Sources in Auditory Scene Analysis
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2610.30874
   Auditory scene analysis (ASA) models extract information about individual sound sources from a complex auditory mixture.
6. In-Orbit Computing for Remote Sensing: Task-Oriented Processing and Transmission
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.30693
   The growing volume and timeliness requirements of remote sensing data are exposing the limitations of the conventional "transmit-then-process" architecture, particularly under intermittent satellite-ground connectivity, constrained downlink bandwidth, and limited onboard computing resources.
7. Unified Projection-Domain Material Decomposition for Energy-Integrating and Photon-Counting CT
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.30440
   Objective: To develop a unified and efficient method for projection-domain material decomposition in spectral computed tomography (CT) that incorporates an arbitrary number of spectral measurements, independent of the acquisition mechanism, without reducing the measurements to two effective energies.
8. A corpus-only AUC diagnostic for pooled speech-based depression detection
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2610.31247
   When clinical speech corpora are pooled for evaluation, corpus membership can itself become predictive if class prevalences differ across sources.
9. Electromagnetic Modeling of Deformation-Based Pinching Antennas
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.30906
   Pinching-antenna systems (PAS) rely on local perturbations of a guiding structure to radiate part of the guided electromagnetic energy, making the physical response of the resulting pinching antenna (PA) fundamental to both guided-wave propagation and free-space radiation.
10. Equivariant Experience Replay for Continual Learning in Imaging Inverse Problems
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.30460
   In this work, we propose Equivariant Experience Replay, a new paradigm for achieving continual learning of deep networks for solving ill-posed imaging inverse problems.
11. Spark-Audio 1.0 Technical Report
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2610.31292
   This paper introduces Spark-Audio 1.0, a speech foundation model trained on domestically produced computing infrastructure.
12. Energy-Efficient Risk-Constrained Adaptive Semantic Communications Under Uncertain Adversarial Threats
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.30911
   Semantic communication systems based on deep joint source-channel coding can provide task-oriented wireless transmission, but adversarial robustness may require substantial radio and receiver-side defensive-computation energy.
13. CoRE: Relating Fine-Grained Chest X-ray Findings in Anatomical Context
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.30584
   Chest X-ray interpretation depends on both the anatomical location of findings and their relationships with other abnormalities.
14. PerMix: Anomalous sound detection by predicting the perturbation ratio of mixed samples
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2610.31434
   In anomalous sound detection based on self-supervised learning, the performance of the detection model largely depends on the selection of the pretext task through which the characteristics of normal data are learned.
15. Beyond Binary Encoding: Qudit-Based QAOA Framework for ML Detection in $M$-QAM MIMO Systems
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.30925
   Maximum likelihood (ML) detection in massive multiple-input multiple-output (MIMO) systems is an NP-hard combinatorial problem whose complexity grows exponentially with the number of transmit antennas and the modulation order.
16. CVP-BAA: Efficiently Adapting Segment Anything Model for Medical Image Segmentation
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.30672
   Various task-specific medical segmentation models have demonstrated strong performance, their heavy reliance on extensive annotations and highly specialized architectures limits their versatility, scalability, and clinical applicability.
17. Signed Wasserstein distance for room impulse response comparison
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2610.31596
   The nature of room impulse response signals is often adverse to a clear evaluation of similarity: they are sparse, rapidly varying, signed signals resulting from the complex interaction of room reflections and phase relationships.
18. Array Rotation in Near-Field ISAC: Communication, Detection, and Estimation Under Low-Complexity Transmit Architectures
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.31136
   This paper studies near-field integrated sensing and communication (ISAC) with a rotatable base-station array under an exact spherical-wave propagation model.
19. GWDM: A Guided Wavelet Diffusion Model for Realistic Histopathology Image Generation
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.30775
   Histopathology images are recognized as a reliable and comprehensive modality for Deep Learning (DL) based diagnosis.
20. FiPA-SR -- FiLM-Conditioned Perceptually Informed Audio Super-Resolution
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2605.30594
   Audio bandwidth extension aims to reconstruct missing high-frequency content from bandlimited signals.
21. Telling Neural Network What We Know: Weight Configuration for RNN and Its Application to NextG Real-Time Neural Receiver
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.31210
   AI-enabled receivers offer a promising approach to adaptive physical-layer processing, but conventional neural receivers often require extensive offline training and computationally expensive backpropagation, limiting their suitability for low-latency cellular systems.
22. H-2DGS: Height-Field Gaussian Splatting for Sharp and Deformable Neurosurgical Surface Reconstruction
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.30910
   Neurosurgical navigation commonly presents magnetic resonance imaging (MRI) as 2D slices, making it difficult to relate the anatomy in those slices to the cortical surface observed through the surgical microscope.
23. ShlokaDhara: A Multi-Speaker Sanskrit Speech Corpus for Learning Meter-Aware Prosody in Text-to-Recitation
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2610.26929
   Sanskrit verse recitation is governed by $\textit{Chandas}$, a strict prosodic framework defined by rhythmic $\textit{Laghu}$ (light) and $\textit{Guru}$ (heavy) syllables.
24. Can An Array of Magnetometers Replace a DVL - A Cram\'{e}r-Rao Bound Analysis
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.31217
   Underwater vehicles rely on noisy dead-reckoning systems, such as Doppler velocity log (DVL)-aided inertial navigation systems, for positioning.
25. Vision Transformers for Estimating Irradiance Using Data Scarce Sky Images
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.30940
   Accurate estimation of diffuse horizontal irradiance (DHI) is critical for optimising photovoltaic system performance and energy forecasting yet remains challenging in regions lacking comprehensive ground-based instrumentation.
26. How Far Can the Gemma 4 Speech Encoder Go Without Changing Its Weights? Saudi and Gulf Arabic Speech Recognition with a Frozen and an Adapter-Augmented Encoder
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2610.28673
   We study the 305M-parameter audio encoder shared by Gemma 4 and EmbeddingGemma 2 (bit-identical to that of Gemma 4 E2B except for the final audio-embedding projection) for Saudi and Gulf Arabic speech recognition, without changing any of its pretrained weights; the adapters of our adapted system are additive and kept separate.
27. Stochastic Geometry Analysis and Optimization for Multi-LEO Satellite-Assisted Communications
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.31373
   Low Earth orbit (LEO) satellites are vital in providing seamless connectivities to ground users (GUs).
28. Bound-Conditioned Latent Inference for Progressive Image Compression
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.30966
   Progressive image compression reconstructs images from prefixes of a single bitstream and therefore involves sequential latent inference under partial observations.
29. Closed-Loop Dual-Reference Guidance for Accent Control in Cross-Lingual Voice Cloning
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2610.29351
   Zero-shot cross-lingual voice cloning often carries the reference speaker's accent into the target language.
30. SR-ANM: A Square-Root Atomic Norm Minimization Estimator for Noise-Robust Direction-of-Arrival Estimation
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.31509
   This paper proposes a Square-root Atomic Norm Minimization (SR-ANM) estimator for direction-of-arrival (DoA) estimation in the single measurement vector (SMV) setting.
31. QICOM: Open-Source Software for Reproducible Image Quality Evaluation, Blinded Assessment, and Radiomic Comparison
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.31218
   QICOM (Quality Image COMparator) is open-source software for quantitative image comparison, paired radiomics, and blinded assessment.
32. Interpretable Embeddings of Speech Enhance and Explain Brain Encoding Performance of Audio Models
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2507.16080
   Speech foundation models (SFMs) are increasingly hailed as powerful computational models of human speech perception.
33. Memory-Augmented Online Test-Time Adaptation for EEG Motor Imagery via Perturbation Consistency and Confidence Calibration
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.30422
   Recently, electroencephalography (EEG)-based brain--computer interfaces (BCIs) have gained traction as portable neural measurement systems.

Sources in this brief: eess.AS (Audio and Speech Processing); eess.IV (Image and Video Processing); eess.SP (Signal Processing).
Selected 33 of 447 available items for this weekly brief.