SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 551–600 of 5629 papers

TitleStatusHype
Training Graph Neural Networks with 1000 LayersCode2
Accelerating Sparse Deep Neural NetworksCode2
FastMoE: A Fast Mixture-of-Expert Training SystemCode2
When Attention Meets Fast Recurrence: Training Language Models with Reduced ComputeCode2
Boundary-Aware Segmentation Network for Mobile and Web ApplicationsCode2
RepVGG: Making VGG-style ConvNets Great AgainCode2
I-BERT: Integer-only BERT QuantizationCode2
JAX MD: A Framework for Differentiable PhysicsCode2
MODNet: Real-Time Trimap-Free Portrait Matting via Objective DecompositionCode2
RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation AlgorithmsCode2
LightSeq: A High Performance Inference Library for TransformersCode2
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech SynthesisCode2
Partial FC: Training 10 Million Identities on a Single MachineCode2
A Tensor Compiler for Unified Machine Learning Prediction ServingCode2
Scaling up Differentially Private Deep Learning with Fast Per-Example Gradient ClippingCode2
Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified FrameworkCode2
FastReID: A Pytorch Toolbox for General Instance Re-identificationCode2
Geomstats: A Python Package for Riemannian Geometry in Machine LearningCode2
Neural Network Compression Framework for fast model inferenceCode2
Deep Snake for Real-Time Instance SegmentationCode2
JAX, M.D.: A Framework for Differentiable PhysicsCode2
Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramCode2
ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsCode2
Positive-Unlabeled Compression on the CloudCode2
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model ParallelismCode2
Asymmetric Non-local Neural Networks for Semantic SegmentationCode2
Habitat: A Platform for Embodied AI ResearchCode2
AutoFocus: Efficient Multi-Scale InferenceCode2
ProxylessNAS: Direct Neural Architecture Search on Target Task and HardwareCode2
SNIPER: Efficient Multi-Scale TrainingCode2
geomstats: a Python Package for Riemannian Geometry in Machine LearningCode2
Efficient Neural Audio SynthesisCode2
AMC: AutoML for Model Compression and Acceleration on Mobile DevicesCode2
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts LayerCode2
Feature Pyramid Networks for Object DetectionCode2
GPflow: A Gaussian process library using TensorFlowCode2
Quantized Neural Networks: Training Neural Networks with Low Precision Weights and ActivationsCode2
Fast Algorithms for Convolutional Neural NetworksCode2
Relative Entropy Pathwise Policy OptimizationCode1
LLMThinkBench: Towards Basic Math Reasoning and Overthinking in Large Language ModelsCode1
FADRM: Fast and Accurate Data Residual Matching for Dataset DistillationCode1
Fast ground penetrating radar dual-parameter full waveform inversion method accelerated by hybrid compilation of CUDA kernel function and PyTorchCode1
Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual TrackingCode1
DIP: Unsupervised Dense In-Context Post-training of Visual RepresentationsCode1
CommVQ: Commutative Vector Quantization for KV Cache CompressionCode1
ConsumerBench: Benchmarking Generative AI Applications on End-User DevicesCode1
Farseer: A Refined Scaling Law in Large Language ModelsCode1
Mutual-Supervised Learning for Sequential-to-Parallel Code TranslationCode1
Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long ContextsCode1
Accelerating AllReduce with a Persistent StragglerCode1
Show:102550
← PrevPage 12 of 113Next →

No leaderboard results yet.