SOTAVerified

Computational Efficiency

Methods and optimizations to reduce the computational resources (e.g., time, memory, or power) needed for training and inference in models. This involves techniques that streamline processing, optimize algorithms, or leverage hardware to enhance performance without compromising accuracy.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1001–1025 of 4891 papers

TitleStatusHype
HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose EstimationCode0
HDMba: Hyperspectral Remote Sensing Imagery Dehazing with State Space ModelCode0
A Fast Bootstrap Algorithm for Causal Inference with Large DataCode0
HAND: Hierarchical Attention Network for Multi-Scale Handwritten Document Recognition and Layout AnalysisCode0
Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage PerspectiveCode0
Hard constraint learning approaches with trainable influence functions for evolutionary equationsCode0
Heron Inference for Bayesian Graphical ModelsCode0
Guaranteed Multidimensional Time Series Prediction via Deterministic Tensor Completion TheoryCode0
HADL Framework for Noise Resilient Long-Term Time Series ForecastingCode0
An Enhanced Zeroth-Order Stochastic Frank-Wolfe Framework for Constrained Finite-Sum OptimizationCode0
Group and Shuffle: Efficient Structured Orthogonal ParametrizationCode0
ModeConv: A Novel Convolution for Distinguishing Anomalous and Normal Structural BehaviorCode0
Arbitrary-Oriented Scene Text Detection via Rotation ProposalsCode0
GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated LearningCode0
Hamiltonian Monte Carlo Acceleration Using Surrogate Functions with Random BasesCode0
GraphQA: Protein Model Quality Assessment using Graph Convolutional NetworkCode0
ArchComplete: Autoregressive 3D Architectural Design Generation with Hierarchical Diffusion-Based UpsamplingCode0
Graph Self-Supervised Learning with Learnable Structural and Positional EncodingsCode0
Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural NetworksCode0
Graph neural networks informed locally by thermodynamicsCode0
Graph Neural Networks for modelling breast biomechanical compressionCode0
BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM InferenceCode0
Graph Degree Linkage: Agglomerative Clustering on a Directed GraphCode0
GraphGAN: Graph Representation Learning with Generative Adversarial NetsCode0
Graph Construction with Flexible Nodes for Traffic Demand PredictionCode0
Show:102550
← PrevPage 41 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified