SOTAVerified

GPU

Papers

Showing 801850 of 5629 papers

TitleStatusHype
Dynamic Sparse Training with Structured SparsityCode1
EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANsCode1
Benchmarking of DL Libraries and Models on Mobile DevicesCode1
Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D ScenesCode1
Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval PerformanceCode1
Learning Tracking Representations via Dual-Branch Fully Transformer NetworksCode1
Real-time Semantic Segmentation via Spatial-detail Guided Context PropagationCode1
DLUNet: Semi-supervised Learning based Dual-Light UNet for Multi-organ SegmentationCode1
DM-VTON: Distilled Mobile Real-time Virtual Try-OnCode1
ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution BlocksCode1
Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly DetectionCode1
HRSAM: Efficient Interactive Segmentation in High-Resolution ImagesCode1
Edge and Identity Preserving Network for Face Super-ResolutionCode1
Harmony: Overcoming the Hurdles of GPU Memory Capacity to Train Massive DNN Models on Commodity ServersCode1
HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPSCode1
Harnessing the Power of Large Language Models for Natural Language to First-Order Logic TranslationCode1
Distributed Out-of-Memory NMF on CPU/GPU ArchitecturesCode1
Beyond [cls]: Exploring the true potential of Masked Image Modeling representationsCode1
MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and ResolutionCode1
Gym-μRTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement LearningCode1
BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split ComputingCode1
A Comprehensive Study on Large-Scale Graph Training: Benchmarking and RethinkingCode1
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image DenoisingCode1
ABPN: Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution PhotoCode1
Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement NetworksCode1
Braille Letter Reading: A Benchmark for Spatio-Temporal Pattern Recognition on Neuromorphic HardwareCode1
Efficient Classification of Very Large Images with Tiny ObjectsCode1
EfficientBioAI: Making Bioimaging AI Models Efficient in Energy, Latency and RepresentationCode1
Better, Faster Fermionic Neural NetworksCode1
HAT: Hardware-Aware Transformers for Efficient Natural Language ProcessingCode1
Disentangled High Quality Salient Object DetectionCode1
Benchmarking and scaling of deep learning models for land cover image classificationCode1
Discriminator-Free Generative Adversarial AttackCode1
Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical AnalysisCode1
Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse GradientsCode1
NeuroBack: Improving CDCL SAT Solving using Graph Neural NetworksCode1
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference CostsCode1
In-context Autoencoder for Context Compression in a Large Language ModelCode1
Efficient Forward Architecture SearchCode1
BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity AllocationCode1
BERTVision -- A Parameter-Efficient Approach for Question AnsweringCode1
Graph Neural Networks for Link Prediction with Subgraph SketchingCode1
DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP TrainingCode1
BenchPress: A Deep Active Benchmark GeneratorCode1
Graph Neural Networks for Low-Energy Event Classification & Reconstruction in IceCubeCode1
Interactive Volume Visualization via Multi-Resolution Hash Encoding based Neural RepresentationCode1
Green Hierarchical Vision Transformer for Masked Image ModelingCode1
Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree SearchCode1
Directional Deep Embedding and Appearance Learning for Fast Video Object SegmentationCode1
Direct Differentiable Augmentation SearchCode1
Show:102550
← PrevPage 17 of 113Next →

No leaderboard results yet.