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

Showing 326350 of 4891 papers

TitleStatusHype
Fast Point TransformerCode1
Fast Sequence Based Embedding with Diffusion GraphsCode1
Fast ground penetrating radar dual-parameter full waveform inversion method accelerated by hybrid compilation of CUDA kernel function and PyTorchCode1
Fast Kernel Scene FlowCode1
Boosting Light-Weight Depth Estimation Via Knowledge DistillationCode1
Adaptive Data Optimization: Dynamic Sample Selection with Scaling LawsCode1
Cached Multi-Lora Composition for Multi-Concept Image GenerationCode1
FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective PropagationCode1
Fast Sequence-Based Embedding with Diffusion GraphsCode1
FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated LearningCode1
Fast and Low-Cost Genomic Foundation Models via Outlier RemovalCode1
Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNNCode1
Birdie: Advancing State Space Models with Reward-Driven Objectives and CurriculaCode1
AMR Similarity Metrics from PrinciplesCode1
FAMO: Fast Adaptive Multitask OptimizationCode1
Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time SeriesCode1
Fast ABC-Boost: A Unified Framework for Selecting the Base Class in Multi-Class ClassificationCode1
Fast and Accurate Entity Recognition with Iterated Dilated ConvolutionsCode1
EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNINGCode1
Facial Emotion Recognition: State of the Art Performance on FER2013Code1
Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PCCode1
Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent CodingCode1
ExpoMamba: Exploiting Frequency SSM Blocks for Efficient and Effective Image EnhancementCode1
Fast and Interpretable 2D Homography Decomposition: Similarity-Kernel-Similarity and Affine-Core-Affine TransformationsCode1
FADRM: Fast and Accurate Data Residual Matching for Dataset DistillationCode1
Show:102550
← PrevPage 14 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05Unverified