SOTAVerified

GPU

Papers

Showing 15011550 of 5629 papers

TitleStatusHype
Semantic Labeling of Large-Area Geographic Regions Using Multi-View and Multi-Date Satellite Images and Noisy OSM Training LabelsCode1
Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware SamplingCode1
Momentum Auxiliary Network for Supervised Local LearningCode1
ConsumerBench: Benchmarking Generative AI Applications on End-User DevicesCode1
DLUNet: Semi-supervised Learning based Dual-Light UNet for Multi-organ SegmentationCode1
Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement NetworksCode1
ConStyle v2: A Strong Prompter for All-in-One Image RestorationCode1
MOGPTK: The Multi-Output Gaussian Process ToolkitCode1
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image DenoisingCode1
DM-VTON: Distilled Mobile Real-time Virtual Try-OnCode1
Efficient Large-scale Scene Representation with a Hybrid of High-resolution Grid and Plane FeaturesCode1
ConsistNet: Enforcing 3D Consistency for Multi-view Images DiffusionCode1
Efficient Motion Prediction: A Lightweight & Accurate Trajectory Prediction Model With Fast Training and Inference SpeedCode1
Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised LearningCode1
Beyond [cls]: Exploring the true potential of Masked Image Modeling representationsCode1
Efficient Forward Architecture SearchCode1
MoDL: Model Based Deep Learning Architecture for Inverse ProblemsCode1
Does Long-Term Series Forecasting Need Complex Attention and Extra Long Inputs?Code1
Efficient fine-tuning of 37-level GraphCast with the Canadian global deterministic analysisCode1
DOGE-Train: Discrete Optimization on GPU with End-to-end TrainingCode1
ModeTv2: GPU-accelerated Motion Decomposition Transformer for Pairwise Optimization in Medical Image RegistrationCode1
Conformer-Kernel with Query Term Independence for Document RetrievalCode1
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference CostsCode1
Efficient Document-level Event Extraction via Pseudo-Trigger-aware Pruned Complete GraphCode1
Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPUCode1
Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless ThreadsCode1
Adjacent Context Coordination Network for Salient Object Detection in Optical Remote Sensing ImagesCode1
Efficient Movie Scene Detection using State-Space TransformersCode1
Model Tells You What to Discard: Adaptive KV Cache Compression for LLMsCode1
MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation CoefficientCode1
DQO-MAP: Dual Quadrics Multi-Object mapping with Gaussian SplattingCode1
DreamShard: Generalizable Embedding Table Placement for Recommender SystemsCode1
Real-time Semantic Segmentation via Spatial-detail Guided Context PropagationCode1
OccamNet: A Fast Neural Model for Symbolic Regression at ScaleCode1
MobileStereoNet: Towards Lightweight Deep Networks for Stereo MatchingCode1
Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile RobotsCode1
Mobile Vision Transformer-based Visual Object TrackingCode1
DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range DataCode1
Efficient Dataset Distillation Using Random Feature ApproximationCode1
DSNAS: Direct Neural Architecture Search without Parameter RetrainingCode1
ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text TranslationCode1
3D Small Object Detection with Dynamic Spatial PruningCode1
Benchmarking and scaling of deep learning models for land cover image classificationCode1
DSXplore: Optimizing Convolutional Neural Networks via Sliding-Channel ConvolutionsCode1
DTL: Disentangled Transfer Learning for Visual RecognitionCode1
iUNets: Fully invertible U-Nets with Learnable Up- and DownsamplingCode1
MMM: Generative Masked Motion ModelCode1
The Signature Kernel is the solution of a Goursat PDECode1
Efficient Crowd Counting via Structured Knowledge TransferCode1
PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory ArchitecturesCode1
Show:102550
← PrevPage 31 of 113Next →

No leaderboard results yet.