Clay weekly context brief for the Systems category (ISO week 2026-W42).

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. Localization in Multi-Panel Massive MIMO With Clock Asynchronism: A Unified Approach
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.12178
   In this work, we propose a unified localization framework, termed UNILocMP, that combines model-based geometry and channel charting (CC) for multi-panel massive multiple-input-multiple-output (MIMO) under clock asynchronism.
2. Skeleton-Guided Progressive Test-Time Adaptation for Thin Curvilinear Structures
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.11104
   Accurate segmentation of thin curvilinear structures is vital for various real-world applications, from vessel analysis to road extraction.
3. A Hybrid Classical-Learning Framework for Adaptive Decision Directed Speech Enhancement
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2609.26183
   Speech enhancement aims to recover clean speech signals from noisy observations while preserving speech quality and intelligibility.
4. Low-complexity Equalization of Zak-OTFS Via Neumann Series
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.10872
   We describe a general method for selecting an orthonormal basis of carrier waveforms that aligns the basis with delay / Doppler characteristics of a wireless channel.
5. Improving Image-Based Nutrition Estimation Through Multimodal Food-Item Verification and Recovery
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.11144
   Single-image nutrition estimation can fail silently when visible foods are missed.
6. Towards Balanced Spectral Reconstruction: Spectrally Adaptive Loss for Streaming Speech Enhancement
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2608.30739
   This paper proposes two spectrally weighted STFT loss functions for lightweight streaming speech enhancement, addressing the magnitude over-attenuation in mid-to-high frequency regions caused by the magnitude-phase compensation effect.
7. Flexible Analog Self-Interference Cancellation for Waveform-Robust Monostatic ISAC
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.10997
   Monostatic integrated sensing and communication (ISAC) requires in-band full-duplex operation, where self-interference cancellation (SIC) must suppress the strong transmit leakage while preserving weak sensing echoes.
8. A Unified Score Matching Paradigm for Video Anomaly Detection and Anticipation
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.11149
   Video anomaly detection (VAD) is a fundamental and safety-critical task in computer vision.
9. Hearing Like Humans? Sound Symbolism and Perceptual Alignment in Speech Language Models
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2607.10162
   Sound symbolism, the human tendency to map speech sounds to perceptual qualities such as roundness or sharpness, arises primarily from the acoustics of speech rather than spelling.
10. 2D Coprime Pilots for Delay-Doppler Sensing in OFDM-ISAC Systems
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.11172
   Integrated Sensing and Communication (ISAC) is envisioned to endow future 6G systems with seamless sensing capabilities.
11. Localization of Candidate Kikuchi Regions in RHEED Images: Visibility and Annotation Boundaries
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.11232
   Kikuchi lines and bands in reflection high-energy electron diffraction (RHEED) carry information on crystal geometry and electron scattering, but are often obscured by intense diffraction streaks.
12. TRACE-EVC: Text-Guided Relative Affective Control for Zero-Shot Emotional Voice Conversion
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2607.03666
   Traditional emotional voice conversion (EVC) conditions generation on explicit target emotions like labels or references, defining the target affective state but omitting the direction or nature of the transition.
13. Integrity and Credibility in Navigation: From Error Characterization to Operational Assuran
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.11190
   Navigation integrity and estimator credibility use error and uncertainty information to address different questions.
14. Open-Vocabulary Audio-Visual Event Localization via Complex-Valued Fusion
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.11846
   Open-Vocabulary Audio-Visual Event Localization (OV-AVEL) labels each video segment with an event class, including classes that were never seen during training.
15. Quantifying Cross-Lingual Transfer in Paralinguistic Speech Tasks
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2603.08231
   Paralinguistic speech tasks are often considered relatively language-agnostic, as they rely on extralinguistic acoustic cues rather than lexical content.
16. gr-ntnisac: An Open GNU Radio Testbed for NTN-ISAC
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.11307
   A passive receiver can sense nearby objects from the echoes of a 5G downlink.
17. LVS: Local View Synthesis from Relative Camera Pose by Reusing Previous Views
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2610.12127
   Interactive scene exploration requires frequent view updates, although small camera motions preserve much of the visible content.
18. An Empirical Analysis of Task-Induced Encoder Bias in Fr\'echet Audio Distance
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2602.23958
   Fr\'echet Audio Distance (FAD) is the de facto standard for evaluating text-to-audio generation, yet its scores depend on the underlying encoder's embedding space.
19. Unrolled Time-Varying Graph Signal Restoration under Spatiotemporal Smoothness Priors
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.11359
   In this paper, we propose restoration methods for time-varying graph signals using deep algorithm unrolling (DAU).
20. VesselSDF: Distance Field Priors for Vascular Network Reconstruction
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2506.16556
   Accurate segmentation of vascular networks from sparse CT scan slices remains a significant challenge in medical imaging, particularly due to the thin, branching nature of vessels and the inherent sparsity between imaging planes.
21. [b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2602.18899
   Self-supervised speech models (S3Ms) are known to encode rich phonetic information, yet how this information is structured remains underexplored.
22. An Embodied Multiagent Framework Based on Token Communications for Cooperative ISAC
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.11434
   The emerging low-altitude economy demands unmanned aerial vehicle (UAV)-enabled integrated sensing and communication (ISAC) for reliable connectivity and environmental awareness.
23. Distribution-Aligned Representation Adaptation for DJSCC over Hybrid Wireless-Wired Networks
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2510.13422
   Deep joint source-channel coding (DJSCC) has emerged as a robust alternative to traditional separate coding for communications through wireless channels.
24. WorldSonus: Bringing Sound to Worlds
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2610.08760
   Recent advances in world models have enabled increasingly realistic visual synthesis.
25. Model-Driven Deep Learning with Rank-One Sensing for Efficient CSI Feedback
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.11558
   Downlink channel state information (CSI) feedback is essential for beamforming optimization in frequency-division duplex (FDD) massive multiple-input multiple-output (MIMO) systems.
26. Revisiting Integration of Image and Metadata for DICOM Series Classification: Cross-Attention and Dictionary Learning
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2602.23833
   Automated identification of DICOM image series is essential for large-scale medical image analysis, quality control, protocol harmonization, and reliable downstream processing.
27. Pronunciation-Oriented Reinforcement Learning for Japanese Text-to-Speech with Kana-Domain ASR Rewards
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2610.07575
   Character error rate (CER) computed by automatic speech recognition (ASR) is widely used as an intelligibility reward for reinforcement learning (RL) post-training of text-to-speech (TTS) systems.
28. An Efficient Correlation-based Evaluation of the GN-Model for General Multi-Span Optical Systems
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.11624
   Accurate and computationally efficient evaluation of non-linear interference (NLI) remains challenging in multi-band WDM systems comprising heterogeneous spans and nonidentical channels.
29. SCI-Mamba: Unsupervised Learning based Low-Light Image Enhancement for Non-Cooperative Spacecraft
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2607.08033
   Low-light visual perception acts as the core visual foundation for on-orbit servicing missions targeting non-cooperative spacecraft, supporting autonomous rendezvous, pose estimation, component detection and robotic capture operations.
30. AccentCL: Robust Accent Classification with Incremental Expansion
   Source: eess.AS (Audio and Speech Processing)
   Link: https://arxiv.org/abs/2610.07426
   Accent classifiers are typically trained with a fixed label inventory and cannot accommodate new accent categories as new data becomes available.
31. Outage-Aware Robust Sensing for UAV ISAC Systems
   Source: eess.SP (Signal Processing)
   Link: https://arxiv.org/abs/2610.11720
   Integrated sensing and communications (ISAC) infrastructure can provide an external perception layer for aerial robots, but dynamic blockage makes the set of informative sensing links at the next update uncertain.
32. Reliability assessment and multicenter clinical application of magnetic resonance methods for knee cartilage quantification
   Source: eess.IV (Image and Video Processing)
   Link: https://arxiv.org/abs/2609.08081
   Background: This study evaluated interreader agreement and longitudinal performance of MRI methods for knee cartilage volume, thickness, and defect-area quantification.

Sources in this brief: eess.AS (Audio and Speech Processing); eess.IV (Image and Video Processing); eess.SP (Signal Processing).
Selected 32 of 440 available items for this weekly brief.