Clay weekly context brief for the Systems category (ISO week 2026-W47). 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. Physics-based simulation unlocks scaling laws for generalizable MRI reconstruction Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2611.15758 Deep-learning-based magnetic resonance imaging (MRI) reconstruction holds great promise for accelerating acquisitions, yet its clinical translation remains bottlenecked by poor generalizability across unseen scanners, populations, anatomies, and protocols. 2. Joint Beamforming and Duplex-Mode Segment Selection for Secure Uplink Transmission in Pinching Antenna Systems Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2611.14712 Pinching antenna systems (PASS) have recently emerged as a promising architecture for reconfigurable, flexible and proximity-driven signal delivery. 3. XingChen-UniFE: A Unified Generative Speech Front-End via Complementary Acoustic-Semantic Modeling Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2610.29164 This paper presents XingChen-UniFE, a unified large audio language model (LALM) for general speech restoration (GSR) and target speaker extraction (TSE). 4. One Block Is Enough: LoopMR for Accelerated MRI Reconstruction Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2611.14947 Deep-learning unrolled networks are the leading approach to accelerated MRI reconstruction. 5. Performance Analysis of Quantization-Aware Neural Channel Estimation with Low-Precision Inference Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2611.14757 Neural channel estimators can improve radio performance of 5G receivers, but real-time deployment in the radio access network (RAN) imposes strict latency and power budgets. 6. Assessing Alignment in Automatic Piano Transcription Datasets: A Benchmark for Scoring Methods Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2611.14443 Automatic Music Transcription (AMT) relies on paired audio--MIDI datasets, implicitly assuming near-perfect temporal alignment. 7. Aggregate Accuracy Hides Diagnosis-Specific Failure in Medical Vision-Language Models Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2611.14975 Medical vision-language models (VLMs) are compared mainly by accuracy averaged across findings, a summary that can hide complete failure on a single diagnosis. 8. Full-Duplex Communication for Pinching Antenna Systems Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2611.14882 This paper investigates multiuser full-duplex (FD) communication assisted by a multiwaveguide pinching-antenna system (PASS) where each dielectric waveguide can be dynamically configured to operate in either downlink transmission or uplink reception mode. 9. Earlybird: Predictive Streaming Speech Recognition in 29M Parameters Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2611.14421 Streaming speech recognizers output a word only after the speaker has finished it, typically 90-400 ms later. 10. Coarse-to-Fine 3D MRI Reconstruction via Resolution-Agnostic Neural Operators Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2611.14979 Deep-learning-based 3D MRI reconstruction is limited in practice by the GPU memory and compute cost of full-volume training; 3D acquisitions are thus most often reconstructed by 2D models applied slice-by-slice and then stacked, which ignores through-plane (stacking-axis) structure. 11. Affine Frequency Division Multiplexing With Pre-Chirp Spreading Index Modulation: A CSI-Driven Secure Transmission Framework Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2611.15045 The flexible configurability of pre-chirp parameters in affine frequency division multiplexing (AFDM) provides new degrees of freedom for designing covert communication mechanisms. 12. Spatio-Temporal Calibration of a Vehicle-Mounted Microphone Array for Autonomous Driving Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2611.14003 Microphones let an autonomous vehicle sense into areas its cameras and LiDAR cannot see, by picking up the sound that other traffic participants emit. 13. Interpreting Selective-Review Coverage for Head-and-Neck Auto-Contours Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2611.15255 Selective-review systems aim to reduce human review by passing candidates predicted to be low risk. 14. Multi-Band Indoor MIMO Channel Measurements Across Sub-6 GHz, Mid-Band and mmWave: Comparing 2.55 GHz, 12.75 GHz and 25.5 GHz Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2611.15285 Future wireless systems for indoor applications are expected to extend their operating frequencies from sub-6 GHz to mid-band and millimeter wave (mmWave) frequencies to support higher data rates. 15. On the information rate of phones, syllables and words Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2611.13990 Which linguistic units minimise the bitrate required to encode speech content: phones, syllables, words, maybe larger units, or something in between? 16. Supervision-Aware Evaluation of MedGemma for Reference-Assisted Radiotherapy Contour Ranking Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2611.15370 Radiotherapy contour ranking can support quality assurance, but vision-language model (VLM) gains may reflect supervision, score construction, available inputs, or representation access. 17. Multi-Label Classification with Constrained Search for Inverse Design of a 16x16 Reconfigurable Pixel Antenna Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2611.15286 In this paper, an inverse design method is presented for a 16x16 reconfigurable pixel antenna with 480 binary switches, giving 2480 possible patterns, far beyond what full-wave simulation can explore. 18. GigaEdge Spench: An SDK for Practical Streaming Speech Enhancement Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2611.13243 We present GigaEdge Spench, an open-source SDK for streaming speech enhancement on CPU servers, mobile devices, and in browsers. 19. HR-NVC++: Unified Ultra-High-Resolution Neural Video Coding with Confidence-Guided Spatial-Temporal Cues Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2611.15670 Ultra-high-resolution neural video coding (NVC) remains challenging because temporal correspondence becomes increasingly unreliable as spatial resolution increases. 20. Analytical Characterization of Radial Resolution at Oblique Angles for Near-Field Communications Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2611.15326 Exploiting radial resolvability in near-field communications requires analytical expressions that directly map physical beam parameters to resolution-controllable focal regions. 21. ESDCodec: Ultra-Low Bitrate Speech Codec with Enhanced Semantic Disentanglement and Subband Decoding Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2611.14043 Despite recent advances in neural speech codecs, achieving highfidelity speech reconstruction at low bitrates remains a formidable challenge. 22. FGCARL: Fisher-Guided Continuously Adaptive Representation Learning for Medical Image Segmentation Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2611.16210 Deep learning (DL) has achieved remarkable success in medical image segmentation by learning data-driven representations from large-scale annotated datasets. 23. Deep Learning-Assisted Optimization of Large Domino-Tiled Phased Arrays for Dual-Band LEO Satellite Communications Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2611.15390 Irregular domino tiling reduces the number of transmit/receive modules (TRMs) of large phased arrays, but its design requires repeated pattern evaluations whose cost grows rapidly with aperture size. 24. Passive ladder-network representation of the radiation impedance of a spherical cap on a rigid sphere Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2611.14016 A loudspeaker in a closed box is modeled as a rigid sphere with an axially moving cap. 25. CODE-PIF: Convex/Deep (CODE) Multiview Pseudoinvariant Features for Multitemporal Multispectral Surface Reflectance Imagery Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2611.16802 Multitemporal multispectral surface reflectance imagery exhibits radiometric and spectral variability due to atmospheric effects, sensor differences, and actual surface changes, complicating the identification of pseudoinvariant features (PIFs). 26. Geometry-based Efficient Airy Beam Training for Quasi-LoS in Terahertz Near-field Communications Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2611.15497 With enlarged antenna apertures in Terahertz (THz) communications, near-field propagation becomes increasingly dominant, highlighting quasi-line-of-sight (quasi-LoS) scenarios with partial blockage. 27. DialInstruct-TTS: Interactive Expressive Speech Generation via Multi-Turn Dialogue with Fine-Grained Temporal Control Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2611.13875 Existing instruction-based TTS systems primarily support one-shot, utterance-level control, where a single instruction determines the speaking style of an entire utterance. 28. Transmission-Mode Multispectral Imaging for Estimation of Microcystis spp. Cell Concentration and ELISA-Equivalent Microcystin Concentration in Water Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2611.16859 Harmful algal blooms dominated by Microcystis spp. 29. A Tutorial on Infrastructure Self-Calibration for Radio-Based Indoor Positioning Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2611.15503 Radio positioning needs the positions of its anchors, access points, base stations, or reconfigurable intelligent surfaces, and manual surveying is costly and error-prone. 30. Walrus Technical Report Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2611.13689 We present Walrus, a unified 8B speech-and-audio foundation model handling speech recognition (including code-switching and multi-talker speech), speech-to-text and speech-to-speech translation, text-to-speech, emotion recognition, audio captioning, and general audio understanding. 31. Data Archive for 2D and 3D Electrical Impedance Tomography with moderate conductivity contrast phantoms Source: eess.IV (Image and Video Processing) Link: https://arxiv.org/abs/2611.17225 This document describes open Electrical Impedance Tomography (EIT) measurement data that were collected from biomedical imaging inspired phantoms with moderate conductivity contrasts. 32. Over-the-Air Computation for Imperfectly Synchronized Multi-View Semantic Communication Source: eess.SP (Signal Processing) Link: https://arxiv.org/abs/2611.15520 Compared to classical task-agnostic communication systems, which focus on reliable transmission of a message, semantic communication (SemCom) focuses on transmitting the task-relevant meaning behind the message. 33. Emilia2: A Large-Scale Dataset for Controllable Long-Form Speech Generation Source: eess.AS (Audio and Speech Processing) Link: https://arxiv.org/abs/2611.13614 Generating long-form speech requires models to keep content, speaker identity, turn-taking, and expressive style consistent over time. Sources in this brief: eess.AS (Audio and Speech Processing); eess.IV (Image and Video Processing); eess.SP (Signal Processing). Selected 33 of 458 available items for this weekly brief.