SOTAVerified

GPU

Papers

Showing 53015350 of 5629 papers

TitleStatusHype
Graph Retention Networks for Dynamic GraphsCode0
Graph Neural Network with Local Frame for Molecular Potential Energy SurfaceCode0
Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action LocalizationCode0
Read, Highlight and Summarize: A Hierarchical Neural Semantic Encoder-based ApproachCode0
deepCR: Cosmic Ray Rejection with Deep LearningCode0
GraphFM: A Comprehensive Benchmark for Graph Foundation ModelCode0
Anchor Space Optimal Transport as a Fast Solution to Multiple Optimal Transport ProblemsCode0
Deep Generalized Convolutional Sum-Product NetworksCode0
Training a Vision Transformer from scratch in less than 24 hours with 1 GPUCode0
Provable Defense Against Geometric TransformationsCode0
Stochastic Gradient Descent on Highly-Parallel ArchitecturesCode0
GraB-sampler: Optimal Permutation-based SGD Data Sampler for PyTorchCode0
Towards Scalable GPU-Accelerated SNN Training via Temporal FusionCode0
Training Deep Nets with Sublinear Memory CostCode0
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman CodingCode0
GQE-Net: A Graph-based Quality Enhancement Network for Point Cloud Color AttributeCode0
Anchors no more: Using peculiar velocities to constrain H_0 and the primordial Universe without calibratorsCode0
Debiasing Cardiac Imaging with Controlled Latent Diffusion ModelsCode0
Real-time Deep Video DeinterlacingCode0
An Analysis of Neural Language Modeling at Multiple ScalesCode0
Streaming-capable High-performance Architecture of Learned Image Compression CodecsCode0
Streaming Generalized Canonical Polyadic Tensor DecompositionsCode0
Benchmarking TPU, GPU, and CPU Platforms for Deep LearningCode0
Real-time End-to-End Video Text Spotter with Contrastive Representation LearningCode0
GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU AccelerationCode0
Benchmarking Keyword Spotting Efficiency on Neuromorphic HardwareCode0
PIM-Opt: Demystifying Distributed Optimization Algorithms on a Real-World Processing-In-Memory SystemCode0
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic SegmentationCode0
GPU-accelerated partially linear multiuser detection for 5G and beyond URLLC systemsCode0
Real-Time Graph-based Point Cloud Networks on FPGAs via Stall-Free Deep PipeliningCode0
GPU Kernels for Block-Sparse WeightsCode0
Alternating Maximization: Unifying Framework for 8 Sparse PCA Formulations and Efficient Parallel CodesCode0
GPU-FV: Realtime Fisher Vector and Its Applications in Video MonitoringCode0
Data Stream Sampling with Fuzzy Task Boundaries and Noisy LabelsCode0
GPU-Based Computation of 2D Least Median of Squares with Applications to Fast and Robust Line DetectionCode0
Dataset Distillation via Adversarial Prediction MatchingCode0
Real-time instance segmentation with polygons using an Intersection-over-Union lossCode0
Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric AnnotationsCode0
Striving for Faster and Better: A One-Layer Architecture with Auto Re-parameterization for Low-Light Image EnhancementCode0
Benchmarking Deep Spiking Neural Networks on Neuromorphic HardwareCode0
GPU-acceleration for Large-scale Tree BoostingCode0
Structural Pruning of Pre-trained Language Models via Neural Architecture SearchCode0
GPU-accelerated real-time stixel computationCode0
Data-Informed Global Sparseness in Attention Mechanisms for Deep Neural NetworksCode0
GPU-Accelerated Optimizer-Aware Evaluation of Submodular Exemplar ClusteringCode0
DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE InferenceCode0
Training of Convolutional Networks on Multiple Heterogeneous Datasets for Street Scene Semantic SegmentationCode0
StyPath: Style-Transfer Data Augmentation For Robust Histology Image ClassificationCode0
Sub-Linear Memory: How to Make Performers SLiMCode0
CytonRL: an Efficient Reinforcement Learning Open-source Toolkit Implemented in C++Code0
Show:102550
← PrevPage 107 of 113Next →

No leaderboard results yet.