SOTAVerified

GPU

Papers

Showing 501550 of 5629 papers

TitleStatusHype
Simple Hardware-Efficient Long Convolutions for Sequence ModelingCode2
Cross-domain Neural Pitch and Periodicity EstimationCode2
ImMesh: An Immediate LiDAR Localization and Meshing FrameworkCode2
Recurrent Vision Transformers for Object Detection with Event CamerasCode2
FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural NetworkCode2
Galvatron: Efficient Transformer Training over Multiple GPUs Using Automatic ParallelismCode2
Instant Volumetric Head AvatarsCode2
TorchOpt: An Efficient Library for Differentiable OptimizationCode2
Efficient Spatially Sparse Inference for Conditional GANs and Diffusion ModelsCode2
Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised LearningCode2
ByteTransformer: A High-Performance Transformer Boosted for Variable-Length InputsCode2
Fast Auto-Differentiable Digitally Reconstructed Radiographs for Solving Inverse Problems in Intraoperative ImagingCode2
YOLOV: Making Still Image Object Detectors Great at Video Object DetectionCode2
Musika! Fast Infinite Waveform Music GenerationCode2
Zeus: Understanding and Optimizing GPU Energy Consumption of DNN TrainingCode2
FRA-RIR: Fast Random Approximation of the Image-source MethodCode2
tntorch: Tensor Network Learning with PyTorchCode2
Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel TransformerCode2
BMInf: An Efficient Toolkit for Big Model Inference and TuningCode2
A Dataset and Explorer for 3D Signed Distance FunctionsCode2
HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic SegmentationCode2
FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech SynthesisCode2
pyVHR: a Python framework for remote photoplethysmographyCode2
DeepLIIF: An Online Platform for Quantification of Clinical Pathology SlidesCode2
Rethinking Visual Geo-localization for Large-Scale ApplicationsCode2
TGL: A General Framework for Temporal GNN Training on Billion-Scale GraphsCode2
Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point CloudsCode2
Tevatron: An Efficient and Flexible Toolkit for Dense RetrievalCode2
E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance SegmentationCode2
LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language ModelsCode2
Accelerated Quality-Diversity through Massive ParallelismCode2
HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and DetectionCode2
TransVOD: End-to-End Video Object Detection with Spatial-Temporal TransformersCode2
Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization SpaceCode2
360MonoDepth: High-Resolution 360deg Monocular Depth EstimationCode2
FinRL-Meta: A Universe of Near-Real Market Environments for Data-Driven Deep Reinforcement Learning in Quantitative FinanceCode2
ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement LearningCode2
gCastle: A Python Toolbox for Causal DiscoveryCode2
Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields ReconstructionCode2
TorchAudio: Building Blocks for Audio and Speech ProcessingCode2
LightSeq2: Accelerated Training for Transformer-based Models on GPUsCode2
Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement LearningCode2
UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene ImageryCode2
CrypTen: Secure Multi-Party Computation Meets Machine LearningCode2
Isaac Gym: High Performance GPU-Based Physics Simulation For Robot LearningCode2
Face.evoLVe: A High-Performance Face Recognition LibraryCode2
Habitat 2.0: Training Home Assistants to Rearrange their HabitatCode2
LoRA: Low-Rank Adaptation of Large Language ModelsCode2
2nd Place Solution for Waymo Open Dataset Challenge -- Real-time 2D Object DetectionCode2
2nd Place Solution for Waymo Open Dataset Challenge - Real-time 2D Object DetectionCode2
Show:102550
← PrevPage 11 of 113Next →

No leaderboard results yet.