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 3926–3950 of 4891 papers

TitleStatusHype
Optimizing Memory Efficiency for Deep Convolutional Neural Networks on GPUs—0
Optimizing Over All Sequences of Orthogonal Polynomials—0
Optimizing Parameter Estimation for Electrochemical Battery Model: A Comparative Analysis of Operating Profiles on Computational Efficiency and Accuracy—0
Optimizing Quantized Neural Networks with Natural Gradient—0
Deep learning of transition probability densities for stochastic asset models with applications in option pricing—0
OptoGPT: A Foundation Model for Inverse Design in Optical Multilayer Thin Film Structures—0
Optuna vs Code Llama: Are LLMs a New Paradigm for Hyperparameter Tuning?—0
Oracle-Efficient Algorithms for Online Linear Optimization with Bandit Feedback—0
Oracle-Efficient Differentially Private Learning with Public Data—0
OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Tracking—0
Orchestration of Emulator Assisted Mobile Edge Tuning for AI Foundation Models: A Multi-Agent Deep Reinforcement Learning Approach—0
Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling—0
Orientation-aware interaction-based deep material network in polycrystalline materials modeling—0
Orthogonal Stochastic Configuration Networks with Adaptive Construction Parameter for Data Analytics—0
OSPC: Artificial VLM Features for Hateful Meme Detection—0
Outlier-aware Tensor Robust Principal Component Analysis with Self-guided Data Augmentation—0
Overcoming the Stability Gap in Continual Learning—0
Overcoming Vocabulary Constraints with Pixel-level Fallback—0
PAC-Bayes Tree: weighted subtrees with guarantees—0
PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer—0
Pairwise Geometric Matching for Large-Scale Object Retrieval—0
PAM-UNet: Shifting Attention on Region of Interest in Medical Images—0
PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion—0
Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables—0
Pan-Sharpening With a Hyper-Laplacian Penalty—0
Show:102550
← PrevPage 158 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified