SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2701–2750 of 5629 papers

TitleStatusHype
Rethinking Feature-Based Knowledge Distillation for Face Recognition—0
BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation—0
MIGPerf: A Comprehensive Benchmark for Deep Learning Training and Inference Workloads on Multi-Instance GPUsCode1
Curvature regularization for Non-line-of-sight Imaging from Under-sampled DataCode0
Local Learning on Transformers via Feature Reconstruction—0
Efficient Movie Scene Detection using State-Space TransformersCode1
Cramming: Training a Language Model on a Single GPU in One DayCode3
Brain Cancer Segmentation Using YOLOv5 Deep Neural Network—0
Scaling Painting Style TransferCode0
Sepformer-based Models: More Efficient Models for Long Sequence Time-Series ForecastingCode1
CDO calibration via Magnus Expansion and Deep LearningCode0
CarFi: Rider Localization Using Wi-Fi CSI—0
Scalable Hybrid Learning Techniques for Scientific Data CompressionCode1
On the Design of Quantum Graph Convolutional Neural Network in the NISQ-Era and BeyondCode0
Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model—0
Hardware Acceleration of Lane Detection Algorithm: A GPU Versus FPGA Comparison—0
Point-E: A System for Generating 3D Point Clouds from Complex PromptsCode5
Person Detection Using an Ultra Low-resolution Thermal Imager on a Low-cost MCU—0
Fast Rule-Based Decoding: Revisiting Syntactic Rules in Neural Constituency Parsing—0
A Study on the Intersection of GPU Utilization and CNN Inference—0
Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razorCode0
Learning a Fast 3D Spectral Approach to Object Segmentation and Tracking over Space and Time—0
DeepJoin: Joinable Table Discovery with Pre-trained Language Models—0
Real-Time Neural Light Field on Mobile DevicesCode1
Cross-Domain Video Anomaly Detection without Target Domain Adaptation—0
RTMDet: An Empirical Study of Designing Real-Time Object DetectorsCode4
An Exploratory Study of AI System Risk Assessment from the Lens of Data Distribution and Uncertainty—0
Single Cell Training on Architecture Search for Image Denoising—0
CNO-LSTM: A Chaotic Neural Oscillatory Long Short-Term Memory Model for Text Classification—0
Recurrent Vision Transformers for Object Detection with Event CamerasCode2
Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detection—0
Elixir: Train a Large Language Model on a Small GPU ClusterCode7
Optimized Sparse Matrix Operations for Reverse Mode Automatic DifferentiationCode1
GPU-accelerated Guided Source Separation for Meeting TranscriptionCode1
Towards a learning-based performance modeling for accelerating Deep Neural Networks—0
TinyKG: Memory-Efficient Training Framework for Knowledge Graph Neural Recommender Systems—0
An Efficient Evolutionary Deep Learning Framework Based on Multi-source Transfer Learning to Evolve Deep Convolutional Neural Networks—0
BiPMAP: A Toolbox for Predictions of Perceived Motion Artifacts on Modern Displays—0
Multi-Objective Linear Ensembles for Robust and Sparse Training of Few-Bit Neural NetworksCode0
Supervised Tractogram Filtering using Geometric Deep LearningCode0
Event-based Monocular Dense Depth Estimation with Recurrent Transformers—0
Vision Transformer Computation and Resilience for Dynamic Inference—0
Bi-Level Optimization Augmented with Conditional Variational Autoencoder for Autonomous Driving in Dense Traffic—0
SoftCTC -- Semi-Supervised Learning for Text Recognition using Soft Pseudo-LabelsCode1
cs-net: structural approach to time-series forecasting for high-dimensional feature space data with limited observations—0
Accelerating Interactive Human-like Manipulation Learning with GPU-based Simulation and High-quality Demonstrations—0
AdaCM: Adaptive ColorMLP for Real-Time Universal Photo-realistic Style Transfer—0
The RoyalFlush System for the WMT 2022 Efficiency Task—0
A Learned Pixel-by-Pixel Lossless Image Compression Method with 59K Parameters and Parallel DecodingCode0
Loss shaping enhances exact gradient learning with Eventprop in spiking neural networksCode1
Show:102550
← PrevPage 55 of 113Next →

No leaderboard results yet.