SOTAVerified

GPU

Papers

Showing 701725 of 5629 papers

TitleStatusHype
Cache Me If You Must: Adaptive Key-Value Quantization for Large Language ModelsCode1
Bringing UMAP Closer to the Speed of Light with GPU AccelerationCode1
Adaptive Two-Stage Cloud Resource Scaling via Hierarchical Multi-Indicator Forecasting and Bayesian Decision-MakingCode1
Flash3D: Super-scaling Point Transformers through Joint Hardware-Geometry LocalityCode1
Flash Invariant Point AttentionCode1
Temporal Gaussian Process Regression in Logarithmic TimeCode1
Fine-tuning of sign language recognition models: a technical reportCode1
FindVehicle and VehicleFinder: A NER dataset for natural language-based vehicle retrieval and a keyword-based cross-modal vehicle retrieval systemCode1
Fine-tuning giant neural networks on commodity hardware with automatic pipeline model parallelismCode1
Fine-Tuning Pre-trained Transformers into Decaying Fast WeightsCode1
A Comprehensive Study on Large-Scale Graph Training: Benchmarking and RethinkingCode1
Anchor-based Large Language ModelsCode1
FFHNet : Generating Multi-Fingered Robotic Grasps for Unknown Objects in Real-timeCode1
FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware ModellingCode1
Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI ReconstructionCode1
Fine-tuning Quantized Neural Networks with Zeroth-order OptimizationCode1
FELARE: Fair Scheduling of Machine Learning Tasks on Heterogeneous Edge SystemsCode1
FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical ImagingCode1
FFB: A Fair Fairness Benchmark for In-Processing Group Fairness MethodsCode1
FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic SegmentationCode1
Benchmarking of DL Libraries and Models on Mobile DevicesCode1
F-coref: Fast, Accurate and Easy to Use Coreference ResolutionCode1
360MonoDepth: High-Resolution 360° Monocular Depth EstimationCode1
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture SearchCode1
AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networksCode1
Show:102550
← PrevPage 29 of 226Next →

No leaderboard results yet.