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 151–175 of 4891 papers

TitleStatusHype
Q-ARDNS-Multi: A Multi-Agent Quantum Reinforcement Learning Framework with Meta-Cognitive Adaptation for Complex 3D Environments—0
Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion—0
NepTrain and NepTrainKit: Automated Active Learning and Visualization Toolkit for Neuroevolution Potentials—0
FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens—0
Sparse Imagination for Efficient Visual World Model Planning—0
LD-RPMNet: Near-Sensor Diagnosis for Railway Point Machines—0
Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs—0
Beyond Attention: Learning Spatio-Temporal Dynamics with Emergent Interpretable Topologies—0
Quantization-based Bounds on the Wasserstein Metric—0
Latent Wavelet Diffusion: Enabling 4K Image Synthesis for Free—0
Neural Network-based Information-Theoretic Transceivers for High-Order Modulation Schemes—0
Label-shift robust federated feature screening for high-dimensional classification—0
Learning to Upsample and Upmix Audio in the Latent Domain—0
The Security Threat of Compressed Projectors in Large Vision-Language Models—0
Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language TranslationCode1
Efficient RAW Image Deblurring with Adaptive Frequency ModulationCode1
Pretraining Deformable Image Registration Networks with Random ImagesCode0
Edge Computing for Physics-Driven AI in Computational MRI: A Feasibility Study—0
TumorGen: Boundary-Aware Tumor-Mask Synthesis with Rectified Flow Matching—0
Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document EmbeddingsCode1
K^2IE: Kernel Method-based Kernel Intensity Estimators for Inhomogeneous Poisson ProcessesCode0
HLSAD: Hodge Laplacian-based Simplicial Anomaly Detection—0
Hyperbolic Dataset DistillationCode0
LLaMA-XR: A Novel Framework for Radiology Report Generation using LLaMA and QLoRA Fine Tuning—0
Evaluating the Efficacy of LLM-Based Reasoning for Multiobjective HPC Job Scheduling—0
Show:102550
← PrevPage 7 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified