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 2401–2425 of 4891 papers

TitleStatusHype
An FPGA-Based Accelerator Enabling Efficient Support for CNNs with Arbitrary Kernel Sizes—0
Bayesian Off-Policy Evaluation and Learning for Large Action Spaces—0
A Self-supervised Pressure Map human keypoint Detection Approch: Optimizing Generalization and Computational Efficiency Across Datasets—0
Global Safe Sequential Learning via Efficient Knowledge TransferCode0
Learning Dual-arm Object Rearrangement for Cartesian Robots—0
Improving Building Temperature Forecasting: A Data-driven Approach with System Scenario Clustering—0
EffLoc: Lightweight Vision Transformer for Efficient 6-DOF Camera Relocalization—0
Tumor segmentation on whole slide images: training or prompting?—0
VOOM: Robust Visual Object Odometry and Mapping using Hierarchical LandmarksCode2
FAST: An Optimization Framework for Fast Additive Segmentation in Transparent ML—0
Emulating the interstellar medium chemistry with neural operators—0
Flexible Robust Optimal Bidding of Renewable Virtual Power Plants in Sequential MarketsCode0
FiT: Flexible Vision Transformer for Diffusion ModelCode3
Network Inversion of Binarised Neural Nets—0
DualView: Data Attribution from the Dual PerspectiveCode0
DB-LLM: Accurate Dual-Binarization for Efficient LLMs—0
Turn Waste into Worth: Rectifying Top-k Router of MoE—0
PhaseEvo: Towards Unified In-Context Prompt Optimization for Large Language Models—0
Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank BanditsCode0
Random Projection Neural Networks of Best Approximation: Convergence theory and practical applications—0
FViT: A Focal Vision Transformer with Gabor FilterCode1
Model Editing by Standard Fine-TuningCode1
Private PAC Learning May be Harder than Online Learning—0
Collaborative Learning with Different Labeling Functions—0
Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning—0
Show:102550
← PrevPage 97 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified