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 2426–2450 of 4891 papers

TitleStatusHype
Closed-form Filtering for Non-linear Systems—0
Multi-Fidelity Methods for Optimization: A Survey—0
Exploiting Estimation Bias in Clipped Double Q-Learning for Continous Control Reinforcement Learning Tasks—0
Oracle-Efficient Differentially Private Learning with Public Data—0
Gaussian Ensemble Belief Propagation for Efficient Inference in High-Dimensional SystemsCode0
Contextual Multinomial Logit Bandits with General Value Functions—0
Mercury: A Code Efficiency Benchmark for Code Large Language ModelsCode2
Anchor-based Large Language ModelsCode1
Accelerating Distributed Deep Learning using Lossless Homomorphic CompressionCode0
On Computationally Efficient Multi-Class Calibration—0
Evolution and Efficiency in Neural Architecture Search: Bridging the Gap Between Expert Design and Automated Optimization—0
Differentially Private Training of Mixture of Experts Models—0
Domain Adaptable Fine-Tune Distillation Framework For Advancing Farm SurveillanceCode0
Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data StreamsCode0
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive LossCode1
AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers—0
Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models—0
CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular FusionCode2
Sparse-VQ Transformer: An FFN-Free Framework with Vector Quantization for Enhanced Time Series Forecasting—0
Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RLCode0
BEBLID: Boosted efficient binary local image descriptorCode2
On the Completeness of Invariant Geometric Deep Learning ModelsCode0
Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image SegmentationCode4
Majority Kernels: An Approach to Leverage Big Model Dynamics for Efficient Small Model Training—0
Partially Stochastic Infinitely Deep Bayesian Neural NetworksCode0
Show:102550
← PrevPage 98 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified