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 201–225 of 4891 papers

TitleStatusHype
RoMe: Towards Large Scale Road Surface Reconstruction via Mesh RepresentationCode2
DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal ForecastingCode2
EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level LatenciesCode2
BiFormer: Vision Transformer with Bi-Level Routing AttentionCode2
PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow PredictionCode2
Fast FullSubNet: Accelerate Full-band and Sub-band Fusion Model for Single-channel Speech EnhancementCode2
Fast-SNARF: A Fast Deformer for Articulated Neural FieldsCode2
Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge DistillationCode2
Simplified State Space Layers for Sequence ModelingCode2
Softmax-free Linear TransformersCode2
ConvMAE: Masked Convolution Meets Masked AutoencodersCode2
Toward Fast, Flexible, and Robust Low-Light Image EnhancementCode2
DaViT: Dual Attention Vision TransformersCode2
Efficient Geometry-aware 3D Generative Adversarial NetworksCode2
MOROCCO: Model Resource Comparison FrameworkCode2
PP-OCR: A Practical Ultra Lightweight OCR SystemCode2
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts LayerCode2
U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKVCode1
FADRM: Fast and Accurate Data Residual Matching for Dataset DistillationCode1
Improve Underwater Object Detection through YOLOv12 Architecture and Physics-informed AugmentationCode1
Fast ground penetrating radar dual-parameter full waveform inversion method accelerated by hybrid compilation of CUDA kernel function and PyTorchCode1
Vectorized Sparse Second-Order Forward Automatic Differentiation for Optimal Control Direct MethodsCode1
It's Not the Target, It's the Background: Rethinking Infrared Small Target Detection via Deep Patch-Free Low-Rank RepresentationsCode1
Attention, Please! Revisiting Attentive Probing for Masked Image ModelingCode1
The Four Color Theorem for Cell Instance SegmentationCode1
Show:102550
← PrevPage 9 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified