SR Transformers
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Rank-Factorized Implicit Neural Bias: Scaling Super-Resolution Transformer with FlashAttention
Announce Type: replace Abstract: Recent Super-Resolution~(SR) methods mainly adopt Transformers for their strong long-range modeling capability and exceptional representational capacity. However, most SR Transformers rely heavily on relative positional bias~(RPB), which prevents them from leveraging hardware-efficient attention kernels such as FlashAttention.
NGram-MoSE: Efficient Remote Sensing Super-Resolution via N-Gram Context and Mixture-of-Experts
Announce Type: new Abstract: Remote sensing applications for environmental monitoring and disaster management are frequently constrained by a spatial--temporal trade-off: imagery with fine spatial detail is often acquired less frequently, whereas more temporally available observations are typically coarser. Single-image super-resolution provides a practical means to enhance coarse imagery without changing acquisition schedules, yet many Transformer-based SR models remain computationally...
An Industrial-Scale Sequential Recommender for LinkedIn Feed Ranking
arXiv:2602.12354v2 Announce Type: replace Abstract: LinkedIn Feed enables professionals worldwide to discover relevant content, build connections, and share knowledge at scale. We present Feed Sequential Recommender (Feed SR), a transformer-based sequential ranking model for LinkedIn Feed that replaces a DCNv2-based ranker and meets strict production constraints. We detail the modeling choices, training techniques, and serving optimizations that enable deployment at a scale of 1.2 billion...
Decomposable Neuro Symbolic Regression
Announce Type: replace Abstract: Symbolic regression (SR) models complex systems by discovering mathematical expressions that capture underlying relationships in observed data. However, most SR methods prioritize minimizing prediction error over identifying the governing equations, often producing overly complex or inaccurate expressions. To address this, we present a decomposable SR method that generates interpretable multivariate expressions leveraging transformer models, genetic...
Beyond Visual Fidelity: Benchmarking Super-Resolution Models for Large-Scale Remote Sensing Imagery via Downstream Task Integration
arXiv:2605.00310v2 Announce Type: replace Abstract: Super-resolution (SR) techniques have made major advances in reconstructing high-resolution images from low-resolution inputs. The increased resolution provides visual enhancement and utility for monitoring tasks. In particular, SR has been increasingly developed for satellite-based Earth observation, with applications in urban planning, agriculture, ecology, and disaster response.
New 'SMArT' platform makes gene editing in hematopoietic stem cells more efficient and safer
New 'SMArT' platform makes gene editing in hematopoietic stem cells more efficient and safer Sadie Harley Scientific Editor Robert Egan Associate Editor A team of researchers led by Luigi Naldini at the San Raffaele Telethon Institute for Gene Therapy (SR-Tiget) has developed a new strategy to significantly improve the precision and safety of CRISPR-Cas9 gene editing in human blood stem cells, potentially overcoming one of the major barriers limiting broader clinical application of genome...
Learning Parametric Nitrogen Fertilizer Response Curves Using Neuro Symbolic Regression
arXiv:2605.31276v1 Announce Type: new Abstract: Accurately modeling crop response to Nitrogen (N) fertilization is a fundamental challenge in precision agriculture, as it impacts both economic returns and environmental sustainability. Existing approaches either rely on predefined parametric forms or opaque machine learning models, limiting their ability to interpret or discover site-specific functional relationships from data. In this work, we propose a neuro symbolic regression (SR)...
Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization
arXiv:2604.08324v3 Announce Type: replace Abstract: Symbolic regression (SR) aims to discover mathematical expressions from data, a task traditionally tackled using Genetic Programming (GP) through combinatorial search over symbolic structures. Latent Space Optimization (LSO) methods use neural encoders to map symbolic expressions into continuous spaces, transforming the combinatorial search into continuous optimization. SNIP (Meidani et al., 2024), a contrastive pre-training model inspired...
MaCo-GAN: Manifold-Contrastive Adversarial Learning for Single Image Super-Resolution
new Abstract: Conventional Generative Adversarial Networks (GANs) for Single Image Super-Resolution (SISR) often struggle with hallucinated artifacts, largely because standard discriminators evaluate overall image naturalness rather than strict conditional realism. To address this, we propose MaCo-GAN, a novel manifold-contrastive GAN framework that replaces the conventional adversarial loss with a supervised contrastive objective. A core component of our method is a dynamic fake sample...
ASUS' ROG Xbox Ally X20 bundle includes a limited-edition OLED Ally X handheld PC and AR gaming glasses
ASUS' ROG Xbox Ally X20 bundle includes a limited-edition OLED Ally X handheld PC and AR gaming glasses The special edition Xbox Ally X has gold accents, too. ASUS is commemorating the 20th anniversary of its Republic of Gamers (ROG) sub-brand with a special edition of its ROG Xbox Ally X handheld gaming PC. Called the ROG Xbox Ally X20, it carries the same hardware as last year's handheld but now comes with a new 7.4-inch 1080p 120Hz OLED panel offering up to 1,400-nit peak brightness and...