Deep Encodings
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Combining Statistical Features and Deep Encodings for Rehearsal-Based Class-Incremental Time Series Classification
arXiv:2606.03292v1 Announce Type: cross Abstract: Many systems used in real-world environments require adding new categories and incorporating new information without forgetting what was previously learnt by the classification model. This is known as class-incremental continual learning, and in the case of multivariate time-series, is further complicated by the temporal structure of the data. In this paper, we present a novel approach for performing class incremental continual learning for...
I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation
Announce Type: replace Abstract: Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained devices remains limited due to their high memory footprint and computational cost. Quantization offers an effective strategy to improve efficiency, but ViT-based segmentation models are notoriously fragile under low precision, as quantization errors accumulate across deep encoder-decoder pipelines. We introduce I-Segmenter,...
When Attention Beats Fourier: Multi-Scale Transformers for PDE Solving on Irregular Domains
arXiv:2605.08318v2 Announce Type: replace Abstract: We study the problem of \emph{architecture selection} for deep learning models trained to solve partial differential equations (PDEs), asking when transformer-based architectures with learned attention outperform Fourier-domain neural operators. We introduce the \textbf{Multi-Scale Attention Transformer} (\msat{}), a deep learning architecture that encodes spatiotemporal solution histories as token sequences and trains end-to-end via a...
When Attention Beats Fourier: Multi-Scale Transformers for PDE Solving on Irregular Domains
arXiv:2605.08318v2 Announce Type: replace-cross Abstract: We study the problem of \emph{architecture selection} for deep learning models trained to solve partial differential equations (PDEs), asking when transformer-based architectures with learned attention outperform Fourier-domain neural operators. We introduce the \textbf{Multi-Scale Attention Transformer} (\msat{}), a deep learning architecture that encodes spatiotemporal solution histories as token sequences and trains end-to-end via...
Physics-Encoded Inverse Modeling for Arctic Snow Depth Prediction
arXiv:2601.17074v4 Announce Type: replace Abstract: Accurate estimation in time-varying inverse problems under limited and sparse observations remains a fundamental challenge across scientific domains. For example, snow depth estimation requires inferring hidden parameters governing sea ice physics, which can be incorporated through physics-informed encoding. To address this challenge, we introduce Physics-Encoded Inversion (PhysE-Inv), a novel framework that combines deep sequential...
Aberration-Free Optical Spectrometer
Announce Type: new Abstract: Optical spectrometers are fundamental to scientific analysis, yet achieving high performance at low cost remains challenging because uncorrected aberrations rapidly degrade spectral resolution and typically necessitate complex, expensive optics. Moreover, to preserve spectral resolution, many compact designs remain fundamentally throughput-limited in terms of having a high f-number and a narrow slit. Here we present SHADES (Stochastic High-throughput...
GalaxyVS: Exploring 100-Billion Compounds in Seconds
We present GalaxyVS, a hardware-software co-designed virtual screening framework built to explore the 100-billion commercially accessible chemical space in seconds, deployed at the National Supercomputing Center in Tianjin. Built upon the dense vector retrieval paradigm of DrugCLIP, GalaxyVS bypasses the structural dependencies and computational overhead of classical docking to enable rapid screening against experimentally determined as well as geometrically feasible pockets on...
Temporally Encoded Double DQN for Proactive PRB Allocation in O-RAN Enabled Industrial Networks
arXiv:2605.30630v1 Announce Type: new Abstract: Fifth-generation (5G) wireless systems are increasingly adopted in smart manufacturing to support heterogeneous industrial workloads through services such as enhanced Mobile Broadband (eMBB) and Ultra-Reliable Low-Latency Communication (URLLC). However, industrial traffic is inherently process-driven and temporally correlated. So, static or reactive schedulers in the Open Radio Access Network (O-RAN) are inadequate for such non-stationary...
ResNet-34 with Lightweight Decoder for Accurate and Efficient Segmentation of Fetal Brain MRI
arXiv:2606.01293v1 Announce Type: cross Abstract: Accurate segmentation of fetal brain tissues in Magnetic Resonance Imaging (MRI) is critical for early diagnosis of congenital abnormalities and improving prenatal care. However, the task remains difficult because of fetal motion, low tissue contrast, and major anatomical variability throughout gestational ages, particularly in segmenting complex structures such as white matter, gray matter, lateral ventricles, deep gray matter,...
Principled Uncertainty in Clinical AI: End-to-End Bayesian Modelling and Algorithmic Equity Auditing Across Multimodal Patient Data
arXiv:2606.09789v1 Announce Type: new Abstract: Clinical artificial intelligence (AI) systems routinely produce predictions without principled quantification of uncertainty, limiting their trustworthiness in high-stakes medical environments. This paper presents an integrated research programme addressing two interconnected problems: (1) the development of a fully end-to-end Bayesian uncertainty modelling framework for multimodal clinical data, and (2) the application of calibrated...