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 526–550 of 4891 papers

TitleStatusHype
CAVM: Conditional Autoregressive Vision Model for Contrast-Enhanced Brain Tumor MRI SynthesisCode1
GLiNER-BioMed: A Suite of Efficient Models for Open Biomedical Named Entity RecognitionCode1
Calibrating LLMs with Information-Theoretic Evidential Deep LearningCode1
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsCode1
CAMP: Collaborative Attention Model with Profiles for Vehicle Routing ProblemsCode1
Global-Local MAV Detection under Challenging Conditions based on Appearance and MotionCode1
Centroid Distance Keypoint Detector for Colored Point CloudsCode1
AIM 2024 Challenge on UHD Blind Photo Quality AssessmentCode1
Geometry-Informed Neural Operator TransformerCode1
BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud RegistrationCode1
Accelerated and interpretable oblique random survival forestsCode1
Cached Multi-Lora Composition for Multi-Concept Image GenerationCode1
Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language TranslationCode1
GMSR:Gradient-Guided Mamba for Spectral Reconstruction from RGB ImagesCode1
Gaussian Kernel Mixture Network for Single Image Defocus DeblurringCode1
AI Accelerator Survey and TrendsCode1
FViT: A Focal Vision Transformer with Gabor FilterCode1
Boosting Light-Weight Depth Estimation Via Knowledge DistillationCode1
GaraMoSt: Parallel Multi-Granularity Motion and Structural Modeling for Efficient Multi-Frame Interpolation in DSA ImagesCode1
Generative Multiplane Neural Radiance for 3D-Aware Image GenerationCode1
Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional NetworksCode1
Activation-Informed Merging of Large Language ModelsCode1
Fully Attentional Network for Semantic SegmentationCode1
Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNNCode1
HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance ScalingCode1
Show:102550
← PrevPage 22 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified