SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1051–1100 of 5629 papers

TitleStatusHype
Marius: Learning Massive Graph Embeddings on a Single MachineCode1
Learning Tracking Representations via Dual-Branch Fully Transformer NetworksCode1
Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion PredictionCode1
Auxiliary Tasks Speed Up Learning PointGoal NavigationCode1
Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and PipeliningCode1
Easy and Efficient Transformer : Scalable Inference Solution For large NLP modelCode1
Autotuning Apache TVM-based Scientific Applications Using Bayesian OptimizationCode1
Latency-aware Spatial-wise Dynamic NetworksCode1
AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal RegularizationCode1
Edge and Identity Preserving Network for Face Super-ResolutionCode1
LAST: Scalable Lattice-Based Speech Modelling in JAXCode1
Latency-aware Unified Dynamic Networks for Efficient Image RecognitionCode1
Auto-scaling Vision Transformers without TrainingCode1
Large Language Model Inference Acceleration: A Comprehensive Hardware PerspectiveCode1
Dynamic Structure Pruning for Compressing CNNsCode1
Large Graph Convolutional Network Training with GPU-Oriented Data Communication ArchitectureCode1
Large Scale Indexing of Generic Medical Image Data using Unbiased Shallow Keypoints and Deep CNN FeaturesCode1
Dynamic Pooling Improves Nanopore Base Calling AccuracyCode1
Dynamic Sparse Training with Structured SparsityCode1
Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded PlatformsCode1
4K-Resolution Photo Exposure Correction at 125 FPS with ~8K ParametersCode1
Dynamic Perceiver for Efficient Visual RecognitionCode1
EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANsCode1
Last Layer Re-Training is Sufficient for Robustness to Spurious CorrelationsCode1
4K-HAZE: A Dehazing Benchmark with 4K Resolution Hazy and Haze-Free ImagesCode1
Automatic Polyp Segmentation with Multiple Kernel Dilated Convolution NetworkCode1
Dynamic GPU Energy Optimization for Machine Learning Training WorkloadsCode1
Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded DevicesCode1
A Hierarchical Spatial Transformer for Massive Point Samples in Continuous SpaceCode1
Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlappingCode1
LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional AdaptationCode1
Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth MapsCode1
Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise SparsityCode1
Dynamic Low-Rank Sparse Adaptation for Large Language ModelsCode1
LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and BenchmarkCode1
Language Embedded 3D Gaussians for Open-Vocabulary Scene UnderstandingCode1
DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence DraftingCode1
DVIS: Decoupled Video Instance Segmentation FrameworkCode1
Efficient Movie Scene Detection using State-Space TransformersCode1
DSXplore: Optimizing Convolutional Neural Networks via Sliding-Channel ConvolutionsCode1
DTL: Disentangled Transfer Learning for Visual RecognitionCode1
Dynamic Mesh-Aware Radiance FieldsCode1
3D Small Object Detection with Dynamic Spatial PruningCode1
Accelerating SNN Training with Stochastic Parallelizable Spiking NeuronsCode1
DXSLAM: A Robust and Efficient Visual SLAM System with Deep FeaturesCode1
Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-ExpertsCode1
Label Supervised LLaMA FinetuningCode1
Large Batch Simulation for Deep Reinforcement LearningCode1
Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: ReportCode1
Low-Precision Arithmetic for Fast Gaussian ProcessesCode1
Show:102550
← PrevPage 22 of 113Next →

No leaderboard results yet.