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 551–575 of 4891 papers

TitleStatusHype
CIS-UNet: Multi-Class Segmentation of the Aorta in Computed Tomography Angiography via Context-Aware Shifted Window Self-AttentionCode1
Learning Hierarchical Image Segmentation For Recognition and By RecognitionCode1
H3DE-Net: Efficient and Accurate 3D Landmark Detection in Medical ImagingCode1
Improving Computational Efficiency in Visual Reinforcement Learning via Stored EmbeddingsCode1
Gracefully Filtering Backdoor Samples for Generative Large Language Models without RetrainingCode1
A Hybrid CNN-BiLSTM Voice Activity DetectorCode1
CAMP: Collaborative Attention Model with Profiles for Vehicle Routing ProblemsCode1
Centroid Distance Keypoint Detector for Colored Point CloudsCode1
GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot LearningCode1
Gradient-free variational learning with conditional mixture networksCode1
BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud RegistrationCode1
Global-Local MAV Detection under Challenging Conditions based on Appearance and MotionCode1
GMSR:Gradient-Guided Mamba for Spectral Reconstruction from RGB ImagesCode1
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image ClassificationCode1
Cached Multi-Lora Composition for Multi-Concept Image GenerationCode1
GLiNER-BioMed: A Suite of Efficient Models for Open Biomedical Named Entity RecognitionCode1
A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and ExplainabilityCode1
A Survey of World Models for Autonomous DrivingCode1
Calibrating LLMs with Information-Theoretic Evidential Deep LearningCode1
Boosting Light-Weight Depth Estimation Via Knowledge DistillationCode1
Geometry-Informed Neural Operator TransformerCode1
A State-Space Perspective on Modelling and Inference for Online Skill RatingCode1
CAVM: Conditional Autoregressive Vision Model for Contrast-Enhanced Brain Tumor MRI SynthesisCode1
GPU optimization of the 3D Scale-invariant Feature Transform Algorithm and a Novel BRIEF-inspired 3D Fast DescriptorCode1
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsCode1
Show:102550
← PrevPage 23 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified