SOTAVerified

GPU

Papers

Showing 10011050 of 5629 papers

TitleStatusHype
GateNet: A novel Neural Network Architecture for Automated Flow Cytometry GatingCode1
Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference ServingCode1
Harmony: Overcoming the Hurdles of GPU Memory Capacity to Train Massive DNN Models on Commodity ServersCode1
FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language ModelsCode1
Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile RobotsCode1
MobileStereoNet: Towards Lightweight Deep Networks for Stereo MatchingCode1
FOVEA: Foveated Image Magnification for Autonomous NavigationCode1
ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM TrainingCode1
From English To Foreign Languages: Transferring Pre-trained Language ModelsCode1
MoDL: Model Based Deep Learning Architecture for Inverse ProblemsCode1
FORK: A Forward-Looking Actor For Model-Free Reinforcement LearningCode1
A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth ImageCode1
ArchesWeather: An efficient AI weather forecasting model at 1.5° resolutionCode1
CommVQ: Commutative Vector Quantization for KV Cache CompressionCode1
Fourier-MIONet: Fourier-enhanced multiple-input neural operators for multiphase modeling of geological carbon sequestrationCode1
FlexModel: A Framework for Interpretability of Distributed Large Language ModelsCode1
BASNet: Boundary-Aware Salient Object DetectionCode1
Accel-GCN: High-Performance GPU Accelerator Design for Graph Convolution NetworksCode1
Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human SupervisionCode1
FlowGNN: A Dataflow Architecture for Real-Time Workload-Agnostic Graph Neural Network InferenceCode1
AKG: Automatic Kernel Generation for Neural Processing Units using Polyhedral TransformationsCode1
FlashMLA-ETAP: Efficient Transpose Attention Pipeline for Accelerating MLA Inference on NVIDIA H20 GPUsCode1
Accelerating Vision-Language Pretraining with Free Language ModelingCode1
Flash Invariant Point AttentionCode1
FL_PyTorch: optimization research simulator for federated learningCode1
CorticalFlow: A Diffeomorphic Mesh Transformer Network for Cortical Surface ReconstructionCode1
Accelerating Translational Image Registration for HDR Images on GPUCode1
Bag of Tricks for Inference-time Computation of LLM ReasoningCode1
Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion ModelsCode1
Flash3D: Super-scaling Point Transformers through Joint Hardware-Geometry LocalityCode1
Fine-Tuning Pre-trained Transformers into Decaying Fast WeightsCode1
Fine-tuning Quantized Neural Networks with Zeroth-order OptimizationCode1
Fine-tuning giant neural networks on commodity hardware with automatic pipeline model parallelismCode1
Fine-tuning of sign language recognition models: a technical reportCode1
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
CoSense3D: an Agent-based Efficient Learning Framework for Collective PerceptionCode1
FFHNet : Generating Multi-Fingered Robotic Grasps for Unknown Objects in Real-timeCode1
FindVehicle and VehicleFinder: A NER dataset for natural language-based vehicle retrieval and a keyword-based cross-modal vehicle retrieval systemCode1
Fully automated analysis of muscle architecture from B-mode ultrasound images with deep learningCode1
FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical ImagingCode1
Auxiliary Tasks Speed Up Learning PointGoal NavigationCode1
Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and PipeliningCode1
F-coref: Fast, Accurate and Easy to Use Coreference ResolutionCode1
Autotuning Apache TVM-based Scientific Applications Using Bayesian OptimizationCode1
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture SearchCode1
AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal RegularizationCode1
FatNet: High Resolution Kernels for Classification Using Fully Convolutional Optical Neural NetworksCode1
Fauno: The Italian Large Language Model that will leave you senza parole!Code1
FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic SegmentationCode1
Show:102550
← PrevPage 21 of 113Next →

No leaderboard results yet.