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 401–425 of 4891 papers

TitleStatusHype
AMD-Hummingbird: Towards an Efficient Text-to-Video ModelCode1
An empirical evaluation of functional alignment using inter-subject decodingCode1
Accel-GCN: High-Performance GPU Accelerator Design for Graph Convolution NetworksCode1
Dual Prototype Evolving for Test-Time Generalization of Vision-Language ModelsCode1
Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language TranslationCode1
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image ClassificationCode1
Dynamic Clustering and Cluster Contrastive Learning for Unsupervised Person Re-identificationCode1
DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion ModelCode1
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot LearningCode1
DQO-MAP: Dual Quadrics Multi-Object mapping with Gaussian SplattingCode1
Dropout Q-Functions for Doubly Efficient Reinforcement LearningCode1
A Simple and Efficient Reconstruction Backbone for Snapshot Compressive ImagingCode1
GraphMamba: An Efficient Graph Structure Learning Vision Mamba for Hyperspectral Image ClassificationCode1
Adapting LLaMA Decoder to Vision TransformerCode1
DnS: Distill-and-Select for Efficient and Accurate Video Indexing and RetrievalCode1
DualOpt: A Dual Divide-and-Optimize Algorithm for the Large-scale Traveling Salesman ProblemCode1
HAAQI-Net: A Non-intrusive Neural Music Audio Quality Assessment Model for Hearing AidsCode1
HabiCrowd: A High Performance Simulator for Crowd-Aware Visual NavigationCode1
DynamicDet: A Unified Dynamic Architecture for Object DetectionCode1
HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic WorkflowsCode1
Heat flux for semi-local machine-learning potentialsCode1
Hexatagging: Projective Dependency Parsing as TaggingCode1
A machine learning-based viscoelastic-viscoplastic model for epoxy nanocomposites with moisture contentCode1
DispFormer: Pretrained Transformer for Flexible Dispersion Curve Inversion from Global Synthesis to Regional ApplicationsCode1
Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation LearningCode1
Show:102550
← PrevPage 17 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified