CNN
-
An Input-Dependent Readout Phase for Resonant Sequence Models
Abstract
Sequence models with a fixed-size state avoid the quadratic cost of attention, but face a design choice. An input-dependent state transition gives content-dependent memory at the cost of FFT-based training, while a fixed transition keeps the O(T log T) convolutional path but reads memory the same way for every input. ResonatorLM, a recent model of the second kind, reads a bank of damped complex oscillators through a fixed learned phase per head. We make that readout phase a function of the current token, which adds input dependence to the read only, keeps the convolution exact, and costs 0.2 percent more parameters. An analysis of the untrained bank shows that phase does encode elapsed time, but an ordinary token falls below the background within 2-8 steps and no choice of damping extends linear reconstruction beyond about 16 tokens. In 6M-parameter character-level models on WikiText-2, the input-dependent phase matches the original at the training length and removes its failure beyond it: trained on 256 tokens and tested on 1024, perplexity falls from 12.81 to 3.76. We trace the failure to long-memory heads that accumulate more history than training exposed them to. The learned phase tracks the current character rather than distance and does not improve retrieval.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12496
PDF
-
Kairos: Toward a Byte-Level Foundation Model for Every Modality
Abstract
Small language models trained on a single local machine leave little room for architectural trial and error. Kairos combines bidirectional gated-DeltaNet linear attention and sliding-window attention over shared projections (LiZAttention2), block-wise Attention-Residual aggregation, a sparse Mixture-of-Experts (MoE) feed-forward layer and a multi-scale byte-level codec, trained with a uniform-noise denoising objective over one byte space shared by text, image, audio, video, lidar and control streams; this report asks whether the combination optimizes at all before asking whether it is useful. We give code-derived algorithms for each component, including a cross-session recurrent-state memory gate, then run convergence sanity checks: overfittinga single 440-byte sentence at 1--15M parameters, text only, with three seeds for codec and attention choices and single-run sweeps for seven further factors. The two attention variants tested at 3\,000 steps (LiZAttention2 and window attention alone) reach a minimum loss near $10^{-3}$. After 600 steps, the mean minimum loss ranges from 0.018 (patch codec) to 0.354 (depthwise convolutional codec) with an identical ranking on three seeds. An apparent advantage of shared over separate attention projections closes with more steps or more diverse data and reverses when the projections are frozen: it is a convergence-speed effect, not a capacity effect. These checks suggest that the implementation optimizes; they say nothing about generalization, multimodal training or comparison with existing models, which a planned pretraining run is meant to address. The Discussion sizes a 200M-total/25M-active target analytically; none of its throughput figures is measured. Code is available at this https URL . Python package at this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2610.12495
PDF
-
NAC: Neural Action Codec for Vision-Language-Action Models
2026-09-25 13:44:37Ahad Jawaid, Yu XiangAbstract
Vision-language-action (VLA) models rely on discrete action tokenizers to bridge continuous robot control and autoregressive sequence modeling, yet existing tokenizers often trade off between compression, latency, and downstream performance. We revisit this design through the lens of neural audio codecs - convolutional encoder-decoder architectures with residual vector quantization that serve as the standard front end for audio foundation models. Motivated by their success, we introduce the Neural Action Codec (NAC), which treats short robot action trajectories as multi-channel 1D signals and compresses them using a multi-scale RVQGAN architecture. With adaptations to the action representation, compression rate, and reconstruction objective, audio-codec-style models can autoencode actions with high fidelity without substantial architectural changes. NAC provides a compact, ordered token space via offset codebooks, enabling standard autoregressive policies to operate over short, structured sequences. Meanwhile, a Vocos-style decoder with an ISTFT head and adversarial discriminators recovers action trajectories. Across LIBERO-10, RoboMimic, and a suite of real-world manipulation tasks, NAC achieves high reconstruction fidelity and higher average success rates than binning, FAST, and prior VQ-based tokenizers at comparable or better compression rates. These results demonstrate that repurposed neural audio codecs offer a strong, practical backbone for learned action tokenization in modern VLAs.
Abstract (translated)
URL
https://arxiv.org/abs/2606.21372
PDF
-
Purin: A Biology-inspired Mechanism for Artificial Neural Networks
2026-09-25 13:15:22Zishu Liu, Chunbo Luo, Christos GrecosAbstract
Artificial neural networks (ANNs) usually represent neural transmission with fixed trainable weights during a training batch, which omits short-term changes in synaptic efficacy. In addition, the discrete time-step simulation requires additional temporal processing that many conventional ANN architectures do not use. To overcome these challenges, we propose Purin, a biology-inspired and ANN-compatible mechanism, that introduces synaptic efficacy modulation into conventional convolutional neural networks. Purin uses a time-interval-based abstraction for neural activities, which allows Purin to introduce short- and long-term synaptic efficacy changes without using discrete time-steps. Purin introduces a bounded factor to represent temporary synaptic efficacy changes, together with two weight matrices that represent input-side and output-side efficacy. The weight matrices are updated by backpropagation and interpreted as the long-term synaptic efficacy changes. Experimental results show that after removing the confounding factors in the AlexNet, VGG11, and GoogLeNet architectures, Purin improves the classification accuracies in all three models across the evaluated datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31235
PDF
-
Teacher-Anchored Selection of Post-Training Quantized Models under Domain Shift
2026-09-25 11:49:05Alejandro Rodriguez Dominguez, Muhammad Shahzad, Xia HongAbstract
Compressing a trained model yields a family of deployment candidates, and under domain shift the most compressed one need not be the one to deploy. We study selection over such a family, with candidates and teacher fixed and target labels absent or scarce. Two findings organize the label-free case. Minimum teacher distortion behaves almost as a constant rule, selecting the same eight-bit, per-channel, unclipped configuration in every run, which does not minimize empirical target cross-entropy. Established estimators divide sharply: in the overconfident-collapse regime of the CNN families, confidence-based estimators order the family close to backwards, and the diagnostics that identify it need the labels the setting denies, while output-distribution estimators match the teacher-relative anchor and on one architecture beat it. Distortion is nonetheless stable, so a supervised term can move selection away from it. Combining the two, we give exact quadratic identities for a canonical quadratic analogue of the family. We also show that under symmetric corruption the label-dependent part of a criterion linear in the label indicator is multiplied by one common factor whenever its coefficient sums are candidate-invariant, a class holding teacher contrasts and accuracy but not cross-entropy. These characterize the score's components without bounding selection regret. Across one hundred and thirty-four candidate families, one per independently trained convolutional or Vision Transformer teacher, anchoring reduces mean regret at the smallest label budget in every setting, an advantage that fades beyond twenty-five labels.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31155
PDF
-
Factorized axis convolutional gated recurrent unit with dynamic adaptive pooling for remaining useful life prediction of rolling bearings
2026-09-25 08:19:02Hanbyeol Park, Jungho Choo, Hyerim BaeAbstract
Convolutional neural networks (CNN) are widely used to predict the remaining useful life (RUL) of rolling bearings from time-frequency representations (TFRs) of vibration signals. However, during degradation, characteristic structures in TFRs align predominantly along the frequency or time axis, making it challenging for conventional CNN isotropic kernels to capture directional structure. Furthermore, global average pooling (GAP) averages across axes, potentially obscuring the locations and concentrations of salient activations. This study introduces a factorized-axis convolutional gated recurrent unit (GRU) that employs multiscale anisotropic convolution and dual-axis convolution block attention module to enhance directional features and highlight salient time-frequency regions. Dynamic adaptive pooling (DAP) adaptively aggregates the time-frequency-axis information from the extracted feature maps, whereas a GRU captures temporal dynamics in the latent representations and Monte Carlo dropout enables predictive uncertainty estimation. Experiments on two public bearing datasets demonstrate that the proposed model outperforms existing RUL prediction methods across operating conditions. Ablation experiments demonstrate that the factorized axis-wise design achieves lower mean errors than convolutional isotropic kernels. DAP yields clear improvements on one dataset while matching GAP on the other, highlighting the importance of anisotropic feature extraction and adaptive feature aggregation for TFR-based RUL prediction.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30972
PDF
-
Training-Free Bottleneck Width Planning for Convolutional Autoencoders
Abstract
Multiscale Spectral Rate-Distortion (MS-SRD) estimates the bottleneck channels required at user-supplied spatial cuts from training images and a normalized mean-squared error (NMSE) bound, without fitting a neural network. Its covariance-tail rule is exact for shared linear block-convolutional autoencoders under squared error. A nested-scale dominance result motivates reporting the activation-parameter Pareto frontier alongside the minimum-latent candidate. At NMSE <= 0.01 on thirteen grayscale datasets, its latent-size prediction has 0.84% mean absolute percentage error against nonlinear patch-autoencoder boundaries; ten predictions are exact and the remaining three differ by one channel. In a four-dataset deployable comparison, MS-SRD matches all retrospective external widths and all four selected models pass, without training a selector; a 46-fit validation grid and four Least-Volume fits each pass on two datasets. In a skip-closed U-shaped autoencoder at the same bound, five predictions are exact, nine are within one channel, and every failing prediction is one channel short. Experiments at looser bounds show progressively larger nonlinear savings.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30755
PDF
-
HCPN-GCN: Scaling Hierarchical Prototype Networks with Cone Geometry for Continual Graph Learning
2026-09-25 01:46:42Sammuel R. Silva, Vander L. S. Freitas, Gladston Moreira, Eduardo J. S. Luz, Rodrigo SilvaAbstract
Continual Graph Learning (CGL) aims to incrementally learn from graph-structured data while preserving knowledge acquired from previous tasks. A major challenge in this setting is catastrophic forgetting, where learning new tasks degrades performance on previously learned ones. Hierarchical Prototype Networks (HPNs) address this problem through a prototype-based memory mechanism that avoids storing historical data, but their reliance on linear feature extractors limits their ability to exploit graph topology, while point-based prototypes often lead to inefficient prototype growth on structurally diverse graphs. In this work, we propose HCPN-GCN, a graph-aware extension of HPN that replaces the original linear feature extractors with Graph Convolutional Networks (GCNs) and introduces cone-based prototypes with a diversity regularization objective. The proposed design produces richer graph-aware representations while compactly modeling the embedding space, reducing prototype proliferation without sacrificing discriminability. Experimental results on six continual graph learning benchmarks demonstrate that HCPN-GCN consistently improves average classification accuracy over the original HPN and representative continual learning baselines while maintaining near-zero forgetting. Furthermore, our analysis shows that the proposed model learns substantially richer class-level prototype hierarchies using approximately $30\times$ fewer atomic prototypes than the original HPN, providing a more compact and effective memory representation for continual graph learning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08823
PDF
-
The Shape of Events: Edge-Based Inductive Biases via Cross-Domain Distillation
2026-09-24 19:17:56Soshun Kihara, Shunsuke Yasuki, Masato TakiAbstract
Convolutional neural networks trained on ImageNet are known to exhibit a strong preference for local high-frequency texture, an inductive bias that translates into fragile robustness against distribution shifts in real-world environments. Event cameras, in contrast, record only changes in scene brightness and are therefore well suited to capturing contour information; however, due to the absence of diagnostic benchmarks in the event domain, the inductive bias that event-camera data instills in vision models has remained underexplored. In this work, we use knowledge distillation from the event domain to the RGB domain so as to exploit the rich evaluation toolkit available in the RGB domain and systematically dissect this inductive bias. Our experiments show that distillation from the event domain induces, in the RGB domain, color invariance, shape bias, and robustness to high-frequency noise. We identify the underlying mechanism as the model suppressing its dependence on high-frequency texture while acquiring a stronger dependence on edge-based object shape. This hypothesis is supported by changes in how color and spatial information are processed at the early layers, together with a spectral trade-off in which robustness to the absence of high-frequency components coexists with vulnerability to contamination of the relied-upon frequency bands and to disruption of geometric structure. We further show that this inductive bias differs from existing robustification methods and that it functions as a useful prior for diverse downstream tasks in which shape and contour information contribute alongside other cues. The code is available at this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2609.30478
PDF
-
Reachability-Based Formal Verification of Graph Neural Networks with Node and Edge Features
2026-09-24 16:29:32Anne M. Tumlin, Ben Wooding, Zhenxuan Shao, Diego Manzanas Lopez, Tyler Derr, Taylor T. JohnsonAbstract
Graph neural networks (GNNs) have become a prominent approach for developing fast, topology-aware surrogates in electric power systems, supporting tasks such as power flow (PF) analysis, optimal power flow (OPF) estimation, and cascading failure analysis (CFA). Despite this growing use, formally verifying GNN-based models remains challenging, with existing methods limited in scope. We extend the neural network verification (NNV) framework to graph-structured inputs through GraphStar sets, a generalization of Star sets that captures uncertainty over both node and edge features. This extension enables the propagation of linear message-passing operations and the sound approximation of ReLU nonlinearities for GNN architectures, including graph convolutional network (GCN) and graph isomorphism network with edge features (GINE) layers. We evaluate GNNV across three power system tasks, PF, OPF, and CFA, on the IEEE-24, IEEE-39, and IEEE-118 test cases, as well as two standard graph classification benchmarks, ENZYMES and PROTEINS. Our results show that GNNV provides tighter robustness guarantees than CORA on graph classification models with ReLU-based activations and, for the first time, delivers edge-aware robustness guarantees for GINE-based PF and OPF models under joint node and edge perturbations.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30079
PDF
-
Beyond Model Size: Redesigning LiSenNet for embedded speech enhancement
2026-09-24 14:24:43Cl\'ement Laroche, Rasmus Kongsgaard OlssonAbstract
Deploying real-time speech enhancement on resource-constrained devices requires meeting strict latency, memory, and energy constraints. Microcontroller NPUs can accelerate neural inference under these constraints, but only through a restricted set of operators in static, integer-quantized graphs. Recent speech-enhancement networks have reduced parameter counts and MACs to levels nominally suitable for microcontrollers, but their operators and execution patterns often remain incompatible with restricted NPUs. We address this gap by redesigning LiSenNet, a 37k parameter sub-band dual-path model, for the STM32N6570-DK Neural-ART accelerator. We replace its recurrent bottleneck with convolutional frequency and temporal mixers, reformulate unsupported operations as static int8-compatible primitives, and use bounded decoder activations to preserve quality after quantization. On VoiceBank-DEMAND, the final NPU-compatible model matches or exceeds the recurrent LiSenNet baseline, reaching PESQ 3.08 versus 3.01 in FP32 and 3.01 versus 2.93 in int8. Deployed on a microcontroller, it processes each 16 ms input hop in 4.83 ms, corresponding to a real-time factor of 0.30. Stateless receptive-field recomputation is an order of magnitude slower at the same frame rate despite higher accelerator utilization. These results show that parameter count and operator compatibility, quantization range, and persistent streaming state must be co-designed to achieve efficient real-time speech enhancement on restricted NPUs.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29866
PDF
-
Lightweight Vision Transformer-Based U-Net for Brain Tumor Segmentation from MRI
2026-09-24 13:26:08Sheekar Banerjee, Md. Srabon Chowdhury, Md. Mahbub Hasan Akash, Ishtiak Al MamoonAbstract
Accurate brain tumor segmentation from Magnetic Resonance Imaging is essential for diagnosis, treatment planning, and surgical guidance. Although Convolutional Neural Networks, particularly UNet, have achieved significant success in medical image segmentation, they often struggle to capture the long-range spatial dependencies required to model tumors with irregular shapes and complex boundaries. This paper proposes a lightweight Vision Transformer UNet that combines the hierarchical feature extraction capability of UNet with the global context modeling of Vision Transformers. The proposed architecture incorporates a compact ViT bottleneck within a U-Net encoder-decoder framework, enabling effective learning of both local and global features while maintaining computational efficiency with only 2.6 million trainable parameters. The model was evaluated on the TCGA LGG MRI Segmentation dataset, achieving a mean Intersection over Union of 0.8100 and a Dice score of 0.8446, outperforming the baseline UNet by 3.75% and 3.15%, respectively. Extensive quantitative and qualitative analyses, including confusion matrix evaluation, precision recall curves, per-image performance distribution, and tumor size dependency analysis, demonstrate the effectiveness and robustness of the proposed method for brain tumor segmentation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29785
PDF
-
A Hybrid CNN--State-Space--Attention Backbone with Joint-Embedding Predictive Pretraining for 12-Lead ECG Classification
2026-09-24 10:58:17Yakoub Bazi, Sarah Aljuhani, Mohamad M. Al Rahhal, Mansour Zuair, Naif AlajlanAbstract
Automatic 12-lead electrocardiogram (ECG) classification requires representations that jointly capture local waveform morphology, long-range temporal dynamics, and cross-lead dependencies, yet integrating these properties within a single efficient architecture remains challenging. This paper introduces a hybrid CNN-SSM-Attention backbone for 12-lead ECG classification. A convolutional stem performs early waveform tokenization and temporal reduction, mixed state-space and depthwise-convolutional blocks model temporal dynamics and local morphology, and a late self-attention stage enables global token interaction at reduced resolution. To improve transfer from unlabeled data, we further develop an ECG-oriented Joint-Embedding Predictive Pretraining (JEPA) framework. Unlike ViT-based JEPA methods that mask patch tokens before the encoder, the proposed method samples span masks at the latent temporal resolution and projects them back to the waveform domain, then predicts clean latent targets from a momentum encoder without waveform reconstruction. Experiments on CPSC2018, Chapman-Shaoxing, and PTB-XL, with pretraining on approximately 350K unlabeled CODE-15 recordings, show that the proposed backbone provides strong supervised baselines under a compact parameter budget. JEPA pretraining further improves transfer, particularly in reduced-label settings and under both full fine-tuning and LoRA-based adaptation. Code: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.29376
PDF
-
A Study of the Limits of Collaborative DCT-Based Image Denoising via Interpretable Neural Networks
2026-09-24 10:07:59Cristian Comellas, Julia Navarro, Antoni BuadesAbstract
Image denoising remains a fundamental problem in image restoration, with applications in photography, biomedical, and scientific imaging. Modern deep neural networks achieve strong performance by learning powerful image priors, but often rely on large black-box models with limited interpretability. In contrast, DCT-based sliding-window and collaborative filtering methods such as BM3D offer clear algorithmic structure, but depend on handcrafted and non-differentiable operations. This work studies how far such structured collaborative filtering principles can be pushed when reformulated as trainable models. We introduce DeepBM3D, a compact fully differentiable architecture that combines non-local patch grouping, DCT-domain filtering, and multi-stage refinement within a BM3D-inspired pipeline. Lightweight convolutional feature extractors guide patch grouping, while filtering is performed through learned Wiener weights in the DCT domain. Experiments show that DeepBM3D improves over classical and hybrid baselines, remains competitive with FFDNet at low and moderate noise levels, and performs particularly well on repetitive textures.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29334
PDF
-
Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting
2026-09-24 09:51:47Xiaohan Jiang, Jingyuan Wang, Jiahao Ji, Yongyao Wang, Chen Yang, Junjie WuAbstract
Time series analysis is fundamental in domains such as finance, healthcare, and meteorology. Real-world time series often exhibit multiscale characteristics shaped by diverse latent factors, resulting in intricate temporal patterns and rich frequency structures. However, existing approaches typically focus on either frequency-domain decomposition or time-domain pattern extraction in isolation, neglecting their joint structure. This decoupled modeling limits representation expressiveness and undermines performance in tasks requiring simultaneous temporal and spectral reasoning. To address this gap, we propose m-WCN, a novel end-to-end deep learning framework that neuralizes multi-wavelet decomposition for joint extraction of temporal patterns and frequency components. By approximating the classical GHM multi-wavelet transform with trainable convolutional operators and enforcing orthogonality constraints, m-WCN produces interpretable multi-resolution representations. Built on this foundation, we introduce two task-specific architectures: TFBC for time series classification, which boosts discriminative features across frequency scales, and FTB for forecasting, which ensembles frequency-aware predictors. Extensive experiments on 64 UCR datasets and seven public forecasting benchmarks demonstrate the effectiveness of our approach. Built on the neuralized m-WCN, our TFBC and FTB outperform various baseline models across diverse datasets, achieving average improvements of 19.97% in classification and 19.92% in forecasting tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29317
PDF
-
Towards Deployable Underwater Vessel Classification
2026-09-24 07:50:50Abishek Soti, Thura Pyae Sone, Naqib Ibnul, Htoo Htet Aung, Henry Zhong, Gregory Cohen, Ying XuAbstract
We propose a compact underwater acoustic classification framework combining multi-representation feature engineering, temporal statistical pooling, and compact convolutional architectures designed for acoustic time-frequency and cochlear representations. We investigate multiple conventional and auditory-inspired representations and first evaluate lightweight classifiers and Conventional Neural Networks (CNNs) on ShipsEar dataset. On the provided split, a two-layer CNN achieves a macro F1 of 0.9918, while a Radial Basis Function Support Vector Machine (RBF-SVM) reaches 0.9883. However, source-recording provenance cannot be reconstructed, preventing verification of recording-independent generalisation. We therefore evaluate on DeepShip dataset using recording-level partitioning before segmentation. Under this protocol, a 157K-parameter compact CNN achieves a test macro F1 of 0.7226, while an 11.17M-parameter ResNet18 provides no improvement in validation performance under the matched setting. These results demonstrate the importance of representation-aware feature and model design, together with rigorous recording-level evaluation, for classification performance and deployability in compact underwater acoustic systems.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29179
PDF
-
Multi-Agent Orchestration of 3GPP Channel Estimators
Abstract
Pilot-aided channel estimation is a decisive block in orthogonal frequency-division multiplexing (OFDM) receivers for both 5G New Radio (5G-NR) and Long-Term Evolution (LTE). A large body of estimators exists, from simple least-squares (LS) interpolation to statistically optimal linear minimum-mean-square-error (LMMSE) variants and, more recently, deep convolutional denoisers, yet no single estimator is uniformly best: the winner depends on the propagation scenario, the numerology, the operating signal-to-noise ratio (SNR), the mobility (Doppler), and the antenna configuration. In this paper, we quantify this fact through a unified study of eight literature estimators evaluated over the 3GPP TR~38.901 Urban-Macro (UMa), Urban-Micro (UMi), and Rural-Macro (RMa) channels generated with NVIDIA Sionna, for both 5G-NR and LTE numerologies, in single-input single-output (SISO) and $8\times2$ multiple-input multiple-output (MIMO) settings. We then propose a \emph{condition-adaptive multi-agent orchestrator} that treats each estimator as an independent agent and dispatches, per operating condition, to the agent that is best on a validation split without any genie knowledge. The orchestrator tracks the per-realization oracle to within $1.07$~dB and improves the normalized mean-square error (NMSE) over the best \emph{fixed} strategy by up to $3.6$~dB at high SNR, where the low-SNR champion is no longer optimal. Because the agents are independent, running them concurrently delivers this best-of-eight accuracy at essentially single-estimator latency: a data-parallel partition scales the wall-clock nearly as $1/K$ with $K$ workers (up to $6.9\times$), whereas naive by-algorithm partitioning is Amdahl-limited by the heaviest agent. The results substantiate multi-agent orchestration as a practical route to robust channel estimation across heterogeneous 5G-NR/LTE deployments.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29044
PDF
-
MicroQonv: Reshaping Convolution Tensors for Efficient Microscaling in Training and Inference
2026-09-23 16:30:48Romain Facq, Sami Ben Ali, Olivier SentieysAbstract
Microscaling quantization techniques are increasingly used to represent neural network parameters with 8 bits or fewer while preserving near-full precision accuracy. However, applying these methods efficiently in convolutional layers is not straightforward. A naive approach transfers full-precision weights and activations to processing units and quantizes each tensor twice, resulting in much more memory movement than expected. Additional overhead comes from the activation tensors, whose sizes grow substantially because of the im2col transformation applied before quantization. We propose MicroQonv, a way to combine microscaling with convolutional layers' forward and backward operations by quantizing each tensor only once and quantizing the activation tensor before applying a modified version of im2col: channel-batch-first im2col. MicroQonv reduces the quantization cost by a factor of $\times2$ for weights and gradients, and by up to $\times9$ for activations, at a negligible accuracy cost. It reduces memory movement and storage by up to $\times7.53$ compared to their full-precision counterparts. This way, MicroQonv reduces microscaling-quantized activation memory movement by $\times3.5$ for state-of-the-art object detection models YOLOV8nano and $\times2.2$ for YOLOV26nano. It also enables 4-bit microscaling in a quantized latent replay strategy for continual learning at the edge, improving accuracy by +5.7% to +11%.
Abstract (translated)
URL
https://arxiv.org/abs/2609.28358
PDF
-
LightMIS: Ultra-Lightweight Medical Image Segmentation Without a Stage-Wise Decoder
2026-09-23 16:05:21Andrei Arhire, Mihaela-Elena Breab\u{a}n, Radu TimofteAbstract
We present LightMIS, a scalable family of ultra-lightweight convolutional networks for 2D binary medical image segmentation without a learned stage-wise decoder. LightMIS aligns the outputs of a five-level encoder to a common resolution using Scale-Aligned Projection blocks, aggregates them once, and refines the fused representation with an Adaptive Fusion Cascade. The cascade combines Adaptive Kernel Fusion with the proposed Progressive Receptive Fusion module, which uses temporary channel expansion, complementary depthwise receptive fields, and progressive cross-branch information transfer. We evaluate LightMIS-T, LightMIS-S, and LightMIS using five-fold cross-validation under a common nnU-Net v2.3.1 protocol on DRIVE, Kvasir-SEG, DSB18, BUSI, ISIC-2017, and ISIC-2018. Full LightMIS contains 0.131 M parameters and requires 0.575 GFLOPs for a $3\times256\times256$ input, achieving modality-macro Dice and IoU scores of 86.71% and 78.99%, respectively. Mobile U-ViT obtains 86.75% Dice and 79.07% IoU, so the observed differences are 0.04 and 0.08 percentage points. Relative to Mobile U-ViT, nnWNet, and nnU-Net, LightMIS reduces parameter count by 90.58$-$99.61% and GFLOPs by 82.54$-$96.14%. On an Arm Mali-G52 MC2 GPU, all LightMIS variants achieve full GPU delegation, with median delegated latency ranging from 53.31 ms for LightMIS-T to 138.31 ms for LightMIS. These results demonstrate a favorable accuracy$-$complexity trade-off and on-device execution feasibility for the evaluated tasks. The code is publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.28327
PDF
-
PBLH Estimation from Satellite Radiances via a Dual-Encoder Transformer
2026-09-23 15:33:02Lorenzo Innocenti, Luca Catalano, Edoardo Arnaudo, Claudio Rossi, Salvatore Larosa, Domenico Cimini, Paolo GarzaAbstract
Estimating the Planetary Boundary Layer Height (PBLH) from satellite observations is a challenging regression problem due to the indirect relationship between top-of-atmosphere radiances and near-surface atmospheric structure. Progress has been limited both by the lack of architectures capable of handling the multimodal, spatially incomplete nature of satellite overpasses, and by the scarcity of suitable datasets. In this paper, we build upon the large-scale dataset pairing MetOp radiances with ERA5 PBLH labels that we introduced in our previous work, making three contributions. First, we establish a benchmark across eight approaches spanning pixel-wise regression, swath-wise sequence models, and convolutional and Transformer models operating on the full orbital passage. Second, we quantify what the resulting model actually relies on, using grouped Shapley decomposition over the input blocks. Third, we present the best-performing architecture found: a dual-encoder Transformer whose masked-input handling lets it operate in all weather conditions. The proposed model achieves MAE = 155.8 m on the held-out global test set, outperforming all baselines on every evaluation subset. On 30 out-of-distribution granules acquired on two days overlapping the TEAMx observational campaign, it achieves MAE = 165.3 m, outperforming a pixel-wise baseline trained on the same data (MAE = 197 m).
Abstract (translated)
URL
https://arxiv.org/abs/2609.28286
PDF
