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 3251–3275 of 4891 papers

TitleStatusHype
Fast and efficient speech enhancement with variational autoencoders—0
Accelerating Parallel Stochastic Gradient Descent via Non-blocking Mini-batches—0
Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean EstimationCode0
Ensemble transport smoothing. Part I: Unified frameworkCode0
QuaLA-MiniLM: a Quantized Length Adaptive MiniLM—0
PAGE: Prototype-Based Model-Level Explanations for Graph Neural NetworksCode1
Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning—0
Neural network-based CUSUM for online change-point detection—0
An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP TasksCode1
Collaborative Honeypot Defense in UAV Networks: A Learning-Based Game Approach—0
BEBERT: Efficient and Robust Binary Ensemble BERTCode0
Joint Semantic Transfer Network for IoT Intrusion Detection—0
Efficient and Effective Augmentation Strategy for Adversarial TrainingCode1
Adaptive physics-informed neural operator for coarse-grained non-equilibrium flows—0
Analyzing Deep Learning Representations of Point Clouds for Real-Time In-Vehicle LiDAR Perception—0
SeismicNet: Physics-informed neural networks for seismic wave modeling in semi-infinite domain—0
Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds—0
Delving into Masked Autoencoders for Multi-Label Thorax Disease ClassificationCode1
Joint Speech Translation and Named Entity Recognition—0
The mass-conversion method: a hybrid technique for simulating well-mixed chemical reaction networks—0
Frequency of Interest-based Noise Attenuation Method to Improve Anomaly Detection Performance—0
gSuite: A Flexible and Framework Independent Benchmark Suite for Graph Neural Network Inference on GPUs—0
Graph sampling for node embedding—0
Accelerate Three-Dimensional Generative Adversarial Networks Using Fast Algorithm—0
Phenomenological Model of Superconducting Optoelectronic Loop Neurons—0
Show:102550
← PrevPage 131 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified