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 4151–4200 of 4891 papers

TitleStatusHype
The deterministic information bottleneckCode0
Rewarded meta-pruning: Meta Learning with Rewards for Channel PruningCode0
HyP-DESPOT: A Hybrid Parallel Algorithm for Online Planning under UncertaintyCode0
Hybrid-MST: A Hybrid Active Sampling Strategy for Pairwise Preference AggregationCode0
RF-BayesPhysNet: A Bayesian rPPG Uncertainty Estimation Method for Complex ScenariosCode0
I Was Blind but Now I See: Implementing Vision-Enabled Dialogue in Social RobotsCode0
WATT-EffNet: A Lightweight and Accurate Model for Classifying Aerial Disaster ImagesCode0
Hybridizing Traditional and Next-Generation Reservoir Computing to Accurately and Efficiently Forecast Dynamical SystemsCode0
SpecNet2: Orthogonalization-free spectral embedding by neural networksCode0
RFR-WWANet: Weighted Window Attention-Based Recovery Feature Resolution Network for Unsupervised Image RegistrationCode0
Hybrid Isolation Forest - Application to Intrusion DetectionCode0
On the Completeness of Invariant Geometric Deep Learning ModelsCode0
Jointly Efficient and Optimal Algorithms for Logistic BanditsCode0
DBgDel: Database-Enhanced Gene Deletion Framework for Growth-Coupled Production in Genome-Scale Metabolic ModelsCode0
On the Computational Efficiency of Training Neural NetworksCode0
Data-to-Model Distillation: Data-Efficient Learning FrameworkCode0
RibSeg v2: A Large-scale Benchmark for Rib Labeling and Anatomical Centerline ExtractionCode0
A Social Robot with Inner Speech for Dietary GuidanceCode0
On the Effectiveness of Incremental Training of Large Language ModelsCode0
Riemannian Laplace Approximation with the Fisher MetricCode0
Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank BanditsCode0
On the Estimation of Entropy in the FastICA AlgorithmCode0
K^2IE: Kernel Method-based Kernel Intensity Estimators for Inhomogeneous Poisson ProcessesCode0
The Framework Tax: Disparities Between Inference Efficiency in NLP Research and DeploymentCode0
KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional ElementsCode0
Hybrid Inexact BCD for Coupled Structured Matrix Factorization in Hyperspectral Super-ResolutionCode0
RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model AccuracyCode0
BioVFM-21M: Benchmarking and Scaling Self-Supervised Vision Foundation Models for Biomedical Image AnalysisCode0
A simple yet effective baseline for non-attributed graph classificationCode0
KernelDNA: Dynamic Kernel Sharing via Decoupled Naive AdaptersCode0
Kernel Heterogeneity Improves Sparseness of Natural Images RepresentationsCode0
Kernel Manifold AlignmentCode0
Efficient Kernel UCB for Contextual BanditsCode0
AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution PredictionCode0
Efficient Human Pose Estimation: Leveraging Advanced Techniques with MediaPipeCode0
HYATT-Net is Grand: A Hybrid Attention Network for Performant Anatomical Landmark DetectionCode0
Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical ModelsCode0
SpectralKAN: Kolmogorov-Arnold Network for Hyperspectral Images Change DetectionCode0
HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge DistillationCode0
Data-driven synchronization-avoiding algorithms in the explicit distributed structural analysis of soft tissueCode0
Data-driven reduced-order modelling for blood flow simulations with geometry-informed snapshotsCode0
Knowledge Distillation by On-the-Fly Native EnsembleCode0
ZeRO-Offload: Democratizing Billion-Scale Model TrainingCode0
On the Steady-State Distributionally Robust Kalman FilterCode0
Efficient Global Multi-object Tracking Under Minimum-cost Circulation FrameworkCode0
Unsupervised Annotation of Phenotypic Abnormalities via Semantic Latent Representations on Electronic Health RecordsCode0
P-Hologen: An End-to-End Generative Framework for Phase-Only HologramsCode0
Unsupervised Discovery of Temporal Structure in Noisy Data with Dynamical Components AnalysisCode0
Efficient Explorative Key-term Selection Strategies for Conversational Contextual BanditsCode0
Biophysically detailed mathematical models of multiscale cardiac active mechanicsCode0
Show:102550
← PrevPage 84 of 98Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified