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 111–120 of 4891 papers

TitleStatusHype
Harder Tasks Need More Experts: Dynamic Routing in MoE ModelsCode2
2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image ClassificationCode2
HeadInfer: Memory-Efficient LLM Inference by Head-wise OffloadingCode2
Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing DetectionCode2
InteractRank: Personalized Web-Scale Search Pre-Ranking with Cross Interaction FeaturesCode2
Long Context is Not Long at All: A Prospector of Long-Dependency Data for Large Language ModelsCode2
LightGNN: Simple Graph Neural Network for RecommendationCode2
MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision TasksCode2
GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-MeshCode2
A Survey on Diffusion Models for Anomaly DetectionCode2
Show:102550
← PrevPage 12 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified