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
Fully 11 Convolutional Network for Lightweight Image Super-ResolutionCode1
Objects do not disappear: Video object detection by single-frame object location anticipationCode1
From continuous-time formulations to discretization schemes: tensor trains and robust regression for BSDEs and parabolic PDEsCode1
Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTMCode1
From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer ParadigmCode1
Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic SegmentationCode1
Fully Attentional Network for Semantic SegmentationCode1
On Evaluation Metrics for Graph Generative ModelsCode1
Focus on Local: Finding Reliable Discriminative Regions for Visual Place RecognitionCode1
FM2S: Towards Spatially-Correlated Noise Modeling in Zero-Shot Fluorescence Microscopy Image DenoisingCode1
FocusTrack: A Self-Adaptive Local Sampling Algorithm for Efficient Anti-UAV TrackingCode1
Cached Multi-Lora Composition for Multi-Concept Image GenerationCode1
Boosting Light-Weight Depth Estimation Via Knowledge DistillationCode1
AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video RecognitionCode1
FlexDiT: Dynamic Token Density Control for Diffusion TransformerCode1
Flash Window Attention: speedup the attention computation for Swin TransformerCode1
A Non-autoregressive Multi-Horizon Flight Trajectory Prediction Framework with Gray Code RepresentationCode1
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsCode1
Algorithmic Differentiation for Automated Modeling of Machine Learned Force FieldsCode1
Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNNCode1
Birdie: Advancing State Space Models with Reward-Driven Objectives and CurriculaCode1
FViT: A Focal Vision Transformer with Gabor FilterCode1
Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics SimulationsCode1
Finer-CAM: Spotting the Difference Reveals Finer Details for Visual ExplanationCode1
Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent CodingCode1
Show:102550
← PrevPage 21 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified