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 501–525 of 4891 papers

TitleStatusHype
Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics DiscoveryCode1
Dual Prototype Evolving for Test-Time Generalization of Vision-Language ModelsCode1
DualOpt: A Dual Divide-and-Optimize Algorithm for the Large-scale Traveling Salesman ProblemCode1
DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion ModelCode1
Objects do not disappear: Video object detection by single-frame object location anticipationCode1
Obtaining Better Static Word Embeddings Using Contextual Embedding ModelsCode1
Offline Reinforcement Learning via High-Fidelity Generative Behavior ModelingCode1
A Simple Local Minimal Intensity Prior and An Improved Algorithm for Blind Image DeblurringCode1
Dropout Q-Functions for Doubly Efficient Reinforcement LearningCode1
Large Language Models Are Not Robust Multiple Choice SelectorsCode1
Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLMCode1
AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video RecognitionCode1
DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote SensingCode1
DnS: Distill-and-Select for Efficient and Accurate Video Indexing and RetrievalCode1
Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object DetectionCode1
Algorithmic Differentiation for Automated Modeling of Machine Learned Force FieldsCode1
DispFormer: Pretrained Transformer for Flexible Dispersion Curve Inversion from Global Synthesis to Regional ApplicationsCode1
DiMoSR: Feature Modulation via Multi-Branch Dilated Convolutions for Efficient Image Super-ResolutionCode1
DiGRAF: Diffeomorphic Graph-Adaptive Activation FunctionCode1
DiRe-JAX: A JAX based Dimensionality Reduction Algorithm for Large-scale DataCode1
Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation LearningCode1
DQO-MAP: Dual Quadrics Multi-Object mapping with Gaussian SplattingCode1
EdgeRegNet: Edge Feature-based Multimodal Registration Network between Images and LiDAR Point CloudsCode1
DeformUX-Net: Exploring a 3D Foundation Backbone for Medical Image Segmentation with Depthwise Deformable ConvolutionCode1
DeepZero: Scaling up Zeroth-Order Optimization for Deep Model TrainingCode1
Show:102550
← PrevPage 21 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified