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 3601–3625 of 4891 papers

TitleStatusHype
Efficient Active Learning for Gaussian Process Classification by Error Reduction—0
Few-Shot Data-Driven Algorithms for Low Rank Approximation—0
Sparse DETR: Efficient End-to-End Object Detection with Learnable SparsityCode1
Characteristic Neural Ordinary Differential Equations—0
Adaptive Fourier Neural Operators: Efficient Token Mixers for TransformersCode1
SpeechMoE2: Mixture-of-Experts Model with Improved Routing—0
Cycle Consistent Probability Divergences Across Different Spaces—0
Dynamic-TinyBERT: Boost TinyBERT's Inference Efficiency by Dynamic Sequence Length—0
Using Convolutional Neural Networks to Detect Compression Algorithms—0
MOROCCO: Model Resource Comparison FrameworkCode2
A Multi-Document Coverage Reward for RELAXed Multi-Document Summarization—0
All Birds with One Stone: Multi-task Learning for Inference with One Forward Pass—0
Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold—0
Fully Linear Graph Convolutional Networks for Semi-Supervised Learning and ClusteringCode0
Uncertainty quantification and inverse modeling for subsurface flow in 3D heterogeneous formations using a theory-guided convolutional encoder-decoder network—0
MC-CIM: Compute-in-Memory with Monte-Carlo Dropouts for Bayesian Edge Intelligence—0
Offline Contextual Bandits for Wireless Network Optimization—0
Observation Error Covariance Specification in Dynamical Systems for Data assimilation using Recurrent Neural Networks—0
Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers—0
Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender SystemsCode1
Statistical and Computational Efficiency for Smooth Tensor Estimation with Unknown Permutations—0
AI challenges for predicting the impact of mutations on protein stability—0
Trajectory PHD and CPHD Filters with Unknown Detection Profile—0
Dual Parameterization of Sparse Variational Gaussian ProcessesCode0
Leveraging Advantages of Interactive and Non-Interactive Models for Vector-Based Cross-Lingual Information Retrieval—0
Show:102550
← PrevPage 145 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified