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
SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over TimeCode1
Hyp2Nav: Hyperbolic Planning and Curiosity for Crowd NavigationCode1
Wavelet-based Bi-dimensional Aggregation Network for SAR Image Change DetectionCode1
Relational Representation DistillationCode1
RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR SegmentationCode1
GraphMamba: An Efficient Graph Structure Learning Vision Mamba for Hyperspectral Image ClassificationCode1
DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote SensingCode1
Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMsCode1
DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable LearnersCode1
DiGRAF: Diffeomorphic Graph-Adaptive Activation FunctionCode1
Hyperspectral Pansharpening: Critical Review, Tools and Future PerspectivesCode1
PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility GraphCode1
Unified Auto-Encoding with Masked DiffusionCode1
CAVM: Conditional Autoregressive Vision Model for Contrast-Enhanced Brain Tumor MRI SynthesisCode1
CE-SSL: Computation-Efficient Semi-Supervised Learning for ECG-based Cardiovascular Diseases DetectionCode1
YOLO9tr: A Lightweight Model for Pavement Damage Detection Utilizing a Generalized Efficient Layer Aggregation Network and Attention MechanismCode1
PixMamba: Leveraging State Space Models in a Dual-Level Architecture for Underwater Image EnhancementCode1
Enhancing Fast Feed Forward Networks with Load Balancing and a Master Leaf NodeCode1
Node Identifiers: Compact, Discrete Representations for Efficient Graph LearningCode1
FTMixer: Frequency and Time Domain Representations Fusion for Time Series ModelingCode1
Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-ContrastCode1
Shallow Recurrent Decoder for Reduced Order Modeling of Plasma DynamicsCode1
Efficient Multi-agent Reinforcement Learning by PlanningCode1
LighTDiff: Surgical Endoscopic Image Low-Light Enhancement with T-DiffusionCode1
Quantum Vision Transformers for Quark-Gluon ClassificationCode1
Show:102550
← PrevPage 17 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified