SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 5001–5050 of 5629 papers

TitleStatusHype
Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated SchedulesCode0
Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU ServersCode0
Learning Versatile Optimizers on a Compute DietCode0
Learning to Rearrange Voxels in Binary Segmentation Masks for Smooth Manifold TriangulationCode0
Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020Code0
Learning to love diligent trolls: Accounting for rater effects in the dialogue safety taskCode0
Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture SearchCode0
Learning to Generate Parameters of ConvNets for Unseen Image DataCode0
DiviML: A Module-based Heuristic for Mapping Neural Networks onto Heterogeneous PlatformsCode0
SNN2ANN: A Fast and Memory-Efficient Training Framework for Spiking Neural NetworksCode0
Bridge the Gap Between Architecture Spaces via A Cross-Domain PredictorCode0
Distributing Deep Learning Hyperparameter Tuning for 3D Medical Image SegmentationCode0
SocioProbe: What, When, and Where Language Models Learn about SociodemographicsCode0
Learning Structured Sparsity in Deep Neural NetworksCode0
Newton-ADMM: A Distributed GPU-Accelerated Optimizer for Multiclass Classification ProblemsCode0
Path-Level Network Transformation for Efficient Architecture SearchCode0
Pathwise CVA Regressions With Oversimulated DefaultsCode0
Learning Guided Convolutional Network for Depth CompletionCode0
SoftMCL: Soft Momentum Contrastive Learning for Fine-grained Sentiment-aware Pre-trainingCode0
Bridging Data Center AI Systems with Edge Computing for Actionable Information RetrievalCode0
PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture SearchCode0
Breast-NET: a lightweight DCNN model for breast cancer detection and grading using histological samplesCode0
PDE-based Group Equivariant Convolutional Neural NetworksCode0
Learning Generative Models with Sinkhorn DivergencesCode0
Learning End-To-End Scene Flow by Distilling Single Tasks KnowledgeCode0
Bottleneck Analysis of Dynamic Graph Neural Network Inference on CPU and GPUCode0
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient PretrainingCode0
Learning Compression from Limited Unlabeled DataCode0
Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads SystemsCode0
Solving ill-posed inverse problems using iterative deep neural networksCode0
BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNetCode0
Learning-based Application-Agnostic 3D NoC Design for Heterogeneous Manycore SystemsCode0
APE: A Data-Centric Benchmark for Efficient LLM Adaptation in Text SummarizationCode0
Distributed Extra-gradient with Optimal Complexity and Communication GuaranteesCode0
Characteristic Performance Study on Solving Oscillator ODEs via Soft-constrained Physics-informed Neural Network with Small DataCode0
Solving the Resource Constrained Project Scheduling Problem Using the Parallel Tabu Search Designed for the CUDA PlatformCode0
EENA: Efficient Evolution of Neural ArchitectureCode0
YOLOBench: Benchmarking Efficient Object Detectors on Embedded SystemsCode0
A parallelized cellular Potts model that enables simulations at tissue scaleCode0
Distilling the Knowledge of Romanian BERTs Using Multiple TeachersCode0
Distilled GPT for Source Code SummarizationCode0
4D-ROLLS: 4D Radar Occupancy Learning via LiDAR SupervisionCode0
Permutohedral Attention Module for Efficient Non-Local Neural NetworksCode0
PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMsCode0
Learned D-AMP: Principled Neural Network based Compressive Image RecoveryCode0
AdaNet: A Scalable and Flexible Framework for Automatically Learning EnsemblesCode0
Distance-Based Tree-Sliced Wasserstein DistanceCode0
Disjunctive Normal NetworksCode0
BlockSwap: Fisher-guided Block Substitution for Network Compression on a BudgetCode0
StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNsCode0
Show:102550
← PrevPage 101 of 113Next →

No leaderboard results yet.