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 901–925 of 4891 papers

TitleStatusHype
Criteria-Aware Graph Filtering: Extremely Fast Yet Accurate Multi-Criteria RecommendationCode0
Linear-Time User-Level DP-SCO via Robust Statistics—0
FLAME: Flexible LLM-Assisted Moderation Engine—0
Neuromorphic Digital-Twin-based Controller for Indoor Multi-UAV Systems Deployment—0
The Paradox of Stochasticity: Limited Creativity and Computational Decoupling in Temperature-Varied LLM Outputs of Structured Fictional Data—0
TANTE: Time-Adaptive Operator Learning via Neural Taylor Expansion—0
Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentationCode1
Contextual Compression Encoding for Large Language Models: A Novel Framework for Multi-Layered Parameter Space Pruning—0
Low-Resolution Neural Networks—0
A Low-Complexity Plug-and-Play Deep Learning Model for Massive MIMO Precoding Across Sites—0
SelfElicit: Your Language Model Secretly Knows Where is the Relevant EvidenceCode1
Recurrent Memory for Online Interdomain Gaussian Processes—0
InTAR: Inter-Task Auto-Reconfigurable Accelerator Design for High Data Volume Variation in DNNsCode1
MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition—0
Filtered Markovian Projection: Dimensionality Reduction in Filtering for Stochastic Reaction NetworksCode0
Exploring Patterns Behind Sports—0
Mesh2SSM++: A Probabilistic Framework for Unsupervised Learning of Statistical Shape Model of Anatomies from Surface MeshesCode0
Fast-COS: A Fast One-Stage Object Detector Based on Reparameterized Attention Vision Transformer for Autonomous Driving—0
Learning Inverse Laplacian Pyramid for Progressive Depth Completion—0
FedAPA: Server-side Gradient-Based Adaptive Personalized Aggregation for Federated Learning on Heterogeneous Data—0
Global Universal Scaling and Ultra-Small Parameterization in Machine Learning Interatomic Potentials with Super-Linearity—0
Long-term simulation of physical and mechanical behaviors using curriculum-transfer-learning based physics-informed neural networks—0
Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive ForecastingCode0
Mixed Integer Linear Programming for Active Contact Selection in Deep Brain Stimulation—0
Provably Efficient RLHF Pipeline: A Unified View from Contextual Bandits—0
Show:102550
← PrevPage 37 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified