Vít
PulseAugur coverage of Vít — every cluster mentioning Vít across labs, papers, and developer communities, ranked by signal.
- developed ScienceCast 90%
- instance of Swin Transformer 90%
- instance of Vision Transformers 90%
- instance of Data Efficient Image Transformers 90%
- used by alphaXiv 70%
- used by DagsHub 70%
- developed Gotit.pub 70%
- used by ScienceCast 70%
- used by CatalyzeX 70%
- instance of alphaXiv 70%
- instance of residual neural network 70%
- developed CatalyzeX 70%
9 day(s) with sentiment data
-
UAV audio classification: Method scaling beats model scaling
A new research paper explores the trade-offs between model size and fine-tuning methods for audio classification on unmanned aerial vehicles (UAVs). The study found that parameter-efficient fine-tuning (PEFT) methods, p…
-
CNN-Transformer Hybrid Achieves 99% Accuracy in Breast Cancer Detection
Researchers have developed a novel deep learning model that integrates Convolutional Neural Networks (CNNs) with Compact Convolutional Transformers (CCT) for improved breast cancer mammography detection and classificati…
-
MAST framework enhances biodiversity sound detection with self-training
Researchers have developed MAST, a novel framework for efficient and robust sound detection in biodiversity monitoring. This approach combines masked audio pretraining with a lightweight detector and iterative self-trai…
-
Looped vs. Stacked Transformers: ECG Classification Comparison
Researchers have conducted a mechanistic comparison between looped and stacked transformer encoders, focusing on their application to 12-lead ECG classification. The study trained two models, bViT (a recurrent transform…
-
New methods tackle test-time adaptation challenges in AI models · 2 sources tracked
Researchers have developed new methods for test-time adaptation in machine learning models. The first approach, MASA, uses a multimodal large language model to anchor semantic descriptions, helping to break a self-refer…
-
CLFTv2: Efficient Camera-LiDAR Fusion for Autonomous Driving
Researchers have introduced CLFTv2, an advanced framework for semantic segmentation in autonomous driving that efficiently fuses camera and LiDAR data. This new model replaces global ViT attention with a Swin-based enco…
-
Pretraining and Distillation Outperform Architecture Choice in Cell Classification
A new study published on arXiv investigates the effectiveness of different deep learning architectures for label-free single-cell classification. The research found that pretraining and fine-tuning strategies are more c…
-
AudioFuse combines ViT and 1D CNN for robust phonocardiogram classification
Researchers have developed AudioFuse, a novel architecture that combines Vision Transformer (ViT) and 1D Convolutional Neural Network (CNN) models to classify phonocardiograms (PCGs). This hybrid approach simultaneously…
-
New CALIPER benchmark reveals limitations in AI visual physics understanding
Researchers have developed a new benchmark called CALIPER to more accurately assess the physical reasoning capabilities of pretrained visual models. Traditional methods using clean, static scenes fail to distinguish bet…
-
AI models for brain MRI match anatomical feature performance
Researchers have conducted a comprehensive evaluation of feature extraction methods for AI models used in structural brain MRI analysis. Their study, which utilized 18 public datasets and approximately 80,000 participan…
-
AI models learn biological concepts for animal re-identification
Researchers have investigated how Vision Transformer (ViT) models used for animal re-identification learn biological concepts without explicit supervision. By fine-tuning a DINOv3 backbone for Western lowland gorilla re…
-
Self-supervised learning models show promise for protein localization in microscopy
A new arXiv paper explores the effectiveness of self-supervised learning (SSL) models for protein localization in microscopy datasets. Researchers found that models pretrained on large datasets like ImageNet-1k and HPA …
-
AI research mimics human vision for efficient visual understanding · 2 papers
Two new research papers propose methods for more efficient visual understanding by mimicking human foveated vision. The first paper introduces FAVE, a variable-resolution ViT that processes selected regions at high acui…
-
CoViT framework enhances Vision Transformers for instance-level perception
Researchers have developed CoViT, a novel self-supervised learning framework designed to enhance Vision Transformers (ViT) for instance-level perception tasks. CoViT addresses ViT's limitation in distinguishing between …
-
Hybrid AI model achieves 99% accuracy in detecting GAN-generated faces
Researchers have developed a novel hybrid architecture that combines EfficientNet-B0's convolutional processing with a Swin Transformer backend for more efficient detection of GAN-generated synthetic faces. This new mod…
-
New HiLRP method offers unified explanation for diverse Vision Transformers
Researchers have developed a new attribution method called HiLRP designed to provide a single, trustworthy explanation for Vision Transformer (ViT) models. Existing methods struggle with the diverse architectures of ViT…
-
Vision Transformer method enhances cancer grading with multimodal data
Researchers have developed a novel semantic-guided multimodal preprocessing technique to improve the grading of clear cell renal cell carcinoma (CCRCC) using Vision Transformers (ViTs). This method integrates nuclei cla…
-
New SARA attack bypasses Vision Transformer privacy defenses
A new research paper details a feature inversion attack called SARA that can reconstruct input images from Vision Transformer (ViT) embeddings transmitted in split-inference systems. The attack demonstrates that token s…
-
DeepSeek V4 multimodal model weights released for inspection
DeepSeek has released the weights and reference code for its V4 multimodal model, allowing researchers to examine its visual processing capabilities. Unlike simple image-to-text additions, V4 integrates visual tokens di…
-
New framework adapts AI models for material recognition from sparse visual data
A new framework called Sparse Surface Understanding Framework (SSUF) has been developed to improve material recognition from incomplete visual data. SSUF adapts four pre-trained architectures—ConvAE, ViT, Swin Transform…