SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1151–1200 of 5629 papers

TitleStatusHype
Last Layer Re-Training is Sufficient for Robustness to Spurious CorrelationsCode1
TALLFormer: Temporal Action Localization with a Long-memory TransformerCode1
Long Movie Clip Classification with State-Space Video ModelsCode1
Stochastic Backpropagation: A Memory Efficient Strategy for Training Video ModelsCode1
Optimization for Classical Machine Learning Problems on the GPUCode1
DELTA: Dynamically Optimizing GPU Memory beyond Tensor RecomputationCode1
A Fast Post-Training Pruning Framework for TransformersCode1
Efficient Visual Tracking via Hierarchical Cross-Attention TransformerCode1
Adjacent Context Coordination Network for Salient Object Detection in Optical Remote Sensing ImagesCode1
Training-free Transformer Architecture SearchCode1
Sionna: An Open-Source Library for Next-Generation Physical Layer ResearchCode1
Mixed-Precision Neural Network Quantization via Learned Layer-wise ImportanceCode1
Panoptic SwiftNet: Pyramidal Fusion for Real-time Panoptic SegmentationCode1
Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol SearchingCode1
Towards Less Constrained Macro-Neural Architecture SearchCode1
DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act RecognitionCode1
End-to-end Multiple Instance Learning with Gradient AccumulationCode1
WaveMix: Resource-efficient Token Mixing for ImagesCode1
Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter PruningCode1
py-irt: A Scalable Item Response Theory Library for PythonCode1
DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN TrainingCode1
Asyncval: A Toolkit for Asynchronously Validating Dense Retriever Checkpoints during TrainingCode1
BERTVision -- A Parameter-Efficient Approach for Question AnsweringCode1
Auto-scaling Vision Transformers without TrainingCode1
Distributed Out-of-Memory NMF on CPU/GPU ArchitecturesCode1
Single UHD Image Dehazing via Interpretable Pyramid NetworkCode1
Benchmarking of DL Libraries and Models on Mobile DevicesCode1
FL_PyTorch: optimization research simulator for federated learningCode1
MariusGNN: Resource-Efficient Out-of-Core Training of Graph Neural NetworksCode1
Harmony: Overcoming the Hurdles of GPU Memory Capacity to Train Massive DNN Models on Commodity ServersCode1
Accelerating DNN Training with Structured Data Gradient PruningCode1
SPDY: Accurate Pruning with Speedup GuaranteesCode1
Convolutional Xformers for VisionCode1
GenGNN: A Generic FPGA Framework for Graph Neural Network AccelerationCode1
Building a Performance Model for Deep Learning Recommendation Model Training on GPUsCode1
Attention-based Proposals Refinement for 3D Object DetectionCode1
SLISEMAP: Supervised dimensionality reduction through local explanationsCode1
OCSampler: Compressing Videos to One Clip with Single-step SamplingCode1
BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split ComputingCode1
GPU-Net: Lightweight U-Net with more diverse featuresCode1
Dynamic GPU Energy Optimization for Machine Learning Training WorkloadsCode1
Scalable semi-supervised dimensionality reduction with GPU-accelerated EmbedSOMCode1
ABPN: Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution PhotoCode1
GPU-accelerated Faster Mean Shift with euclidean distance metricsCode1
GREED: A Neural Framework for Learning Graph Distance FunctionsCode1
Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-ThroughsCode1
NetKet 3: Machine Learning Toolbox for Many-Body Quantum SystemsCode1
GPU optimization of the 3D Scale-invariant Feature Transform Algorithm and a Novel BRIEF-inspired 3D Fast DescriptorCode1
Efficient Document-level Event Extraction via Pseudo-Trigger-aware Pruned Complete GraphCode1
ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor ExtractionCode1
Show:102550
← PrevPage 24 of 113Next →

No leaderboard results yet.