SOTAVerified

CPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 401–450 of 2231 papers

TitleStatusHype
A Case For Adaptive Deep Neural Networks in Edge ComputingCode1
Diet deep generative audio models with structured lotteryCode1
Ultra-light deep MIR by trimming lottery ticketsCode1
Event-based Stereo Visual OdometryCode1
VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial NetworkCode1
Polylidar3D -- Fast Polygon Extraction from 3D DataCode1
OccamNet: A Fast Neural Model for Symbolic Regression at ScaleCode1
Using LSTM and SARIMA Models to Forecast Cluster CPU UsageCode1
Accelerating Translational Image Registration for HDR Images on GPUCode1
Superiority of Simplicity: A Lightweight Model for Network Device Workload PredictionCode1
Enhancing SAT solvers with glue variable predictionsCode1
Hybrid Models for Learning to BranchCode1
Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic AlgorithmCode1
ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret SharingCode1
Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals MeasurementCode1
HAT: Hardware-Aware Transformers for Efficient Natural Language ProcessingCode1
SymJAX: symbolic CPU/GPU/TPU programmingCode1
Optimizing Deep Learning Recommender Systems' Training On CPU Cluster ArchitecturesCode1
Microscopy Image Restoration using Deep Learning on W2SCode1
Fast and Accurate Deep Bidirectional Language Representations for Unsupervised LearningCode1
DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution EnvironmentsCode1
KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflowCode1
Faster than FAST: GPU-Accelerated Frontend for High-Speed VIOCode1
AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal RegularizationCode1
SPFCN: Select and Prune the Fully Convolutional Networks for Real-time Parking Slot DetectionCode1
A new method for faster and more accurate inference of species associations from big community dataCode1
Efficient Intent Detection with Dual Sentence EncodersCode1
Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the WildCode1
Bundle Adjustment on a Graph ProcessorCode1
TFApprox: Towards a Fast Emulation of DNN Approximate Hardware Accelerators on GPUCode1
Training Large Neural Networks with Constant Memory using a New Execution AlgorithmCode1
Real-Time Semantic Background SubtractionCode1
LOGAN: High-Performance GPU-Based X-Drop Long-Read AlignmentCode1
Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPUCode1
Towards Accurate Post-training Network Quantization via Bit-Split and StitchingCode1
Latent Replay for Real-Time Continual LearningCode1
An introductory guide to aligning networks using SANA, the Simulated Annealing Network AlignerCode1
Scientific Image Restoration AnywhereCode1
GPU-Accelerated Viterbi Exact Lattice Decoder for Batched Online and Offline Speech RecognitionCode1
MelGAN: Generative Adversarial Networks for Conditional Waveform SynthesisCode1
Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and MappingCode1
Grid Anchor based Image Cropping: A New Benchmark and An Efficient ModelCode1
Learning to play the Chess Variant Crazyhouse above World Champion Level with Deep Neural Networks and Human DataCode1
Make Skeleton-based Action Recognition Model Smaller, Faster and BetterCode1
And the Bit Goes Down: Revisiting the Quantization of Neural NetworksCode1
High-Performance Deep Learning via a Single Building BlockCode1
Lightweight Network Architecture for Real-Time Action RecognitionCode1
SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning SystemsCode1
ChamNet: Towards Efficient Network Design through Platform-Aware Model AdaptationCode1
MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAMCode1
Show:102550
← PrevPage 9 of 45Next →

No leaderboard results yet.