CORTEXA
← Browse
arxiveess.IVcs.MMeess.SP2026-07-06

Discovering shared interpretable operations in image compression autoencoders

Caroline Mazini Rodrigues, Nicolas Keriven, Thomas Maugey

With the increasing adoption of deep learning for applications such as image compression, improvements in the rate-distortion trade-off have been achieved at the cost of increasingly larger and more opaque ''black-box'' models. Autoencoders are among the most widely used architectures for this task; however, without a clear understanding of their internal behavior, these models tend to grow in complexity to achieve more performance gains. In this paper, we investigate whether universal behaviors can be detected from the internal operations of bias-free autoencoders through Jacobian analysis. If such behaviors exist, they may be extracted to design low-complexity image compression models inspired by high-complexity deep learning architectures.

View free PDFSource page

Related papers

arxivcs.GRcs.ETcs.MMeess.IVeess.SP2026-07-22

Fast Wave-optics Rendering of Multiplane Images for 3D Holographic Displays

Brian Chao, Dario Seyb, Nathan Matsuda, Oliver Cossairt, Yang Zhou, Douglas Lanman, et al.

Recent advances in neural rendering have unlocked unprecedented capabilities in 3D reconstruction and novel view synthesis, giving rise to applications such as virtual fly-throughs of a 3D scene reconstructed from a set of sparse, casually captured images. However, these renderin…

View free PDFSource page
arxivcs.ETeess.IVeess.SPphysics.med-ph2026-07-23

Quantum Adaptive Sensing for Accelerated MRI

Asmit Ganguly, Suprajit Dewanji, Chenyang Zhao, Danny J. J. Wang

Compressed sensing accelerates MRI by reconstructing images from undersampled k-space, but performance depends strongly on sampling distribution. We propose an adaptive framework that selects Cartesian phase-encode lines sequentially using a fixed-cardinality quadratic unconstrai…

View free PDFSource page
arxiveess.IVcs.CVcs.MM2026-07-21

Group-of-Latents: Perceptual Video Compression at Extreme Bitrates via Masked Latent Generative Modeling

Shaokang Wang, Jinchang Xu, Peidong Jia, Zhijian Hao, Siyuan Qian, Fei Zhao, et al.

Most existing video compression algorithms follow a paradigm of transformation and quantization, optimizing the trade-off between distortion and bitrate. However, extremely low-bitrate compression remains an underexplored frontier where perceptual quality optimization under sever…

View free PDFSource page
arxiveess.SYeess.IVeess.SP2026-07-13

WULPUS PRO: Multi-mode Ultra-Low-Power Wearable Ultrasound and Array Imaging with CMUT Support

Sergei Vostrikov, Federico Villani, Cedric Hirschi, Jinhao Lu, Jonas Welsch, Martin Angerer, et al.

Wearable ultrasound enables continuous monitoring of physiological processes such as muscle dynamics, bladder volume, and cardiovascular activity. Existing fully wearable ultra-low-power platforms are limited to shallow, low-channel A-mode sensing, while larger multi-mode systems…

View free PDFSource page
arxiveess.SPcs.CVcs.LGeess.IV2026-07-15

ECG-LLM: Foundation Model for ECG-Based Cardiac Reasoning

Alexander Selivanov, Friederike Jungmann, Jan Kehrer, Karl-Ludwig Laugwitz, Eimo Martens, Daniel Rueckert

Electrocardiography (ECG) is an inexpensive, standard-of-care test for cardiac symptoms, but front-line triage often lacks immediate access to definitive imaging such as echocardiography (ECHO) or cardiac magnetic resonance (CMR). Furthermore, most existing ECGAI systems are limi…

View free PDFSource page