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 4276–4300 of 4891 papers

TitleStatusHype
HADL Framework for Noise Resilient Long-Term Time Series ForecastingCode0
Guaranteed Multidimensional Time Series Prediction via Deterministic Tensor Completion TheoryCode0
All4One: Symbiotic Neighbour Contrastive Learning via Self-Attention and Redundancy ReductionCode0
Learning Gaussian Graphical Models with Ordered Weighted L1 RegularizationCode0
GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated LearningCode0
Cross-Context Backdoor Attacks against Graph Prompt LearningCode0
Multi-head Spatial-Spectral Mamba for Hyperspectral Image ClassificationCode0
Accelerating Bayesian Structure Learning in Sparse Gaussian Graphical ModelsCode0
Learning Joint Denoising, Demosaicing, and Compression from the Raw Natural Image Noise DatasetCode0
3DDX: Bone Surface Reconstruction from a Single Standard-Geometry Radiograph via Dual-Face Depth EstimationCode0
Criteria Tell You More than Ratings: Criteria Preference-Aware Light Graph Convolution for Effective Multi-Criteria RecommendationCode0
Scalable Exploration via Ensemble++Code0
Group and Shuffle: Efficient Structured Orthogonal ParametrizationCode0
Beyond Prediction: On-street Parking Recommendation using Heterogeneous Graph-based List-wise RankingCode0
Learning Mixtures of Plackett-Luce Models from Structured Partial OrdersCode0
Tree-Guided L_1-Convex ClusteringCode0
Criteria-Aware Graph Filtering: Extremely Fast Yet Accurate Multi-Criteria RecommendationCode0
CRISP: Hybrid Structured Sparsity for Class-aware Model PruningCode0
Weighted Anisotropic-Isotropic Total Variation for Poisson DenoisingCode0
CTR-KAN: KAN for Adaptive High-Order Feature Interaction ModelingCode0
GenQ: Quantization in Low Data Regimes with Generative Synthetic DataCode0
Route to Reason: Adaptive Routing for LLM and Reasoning Strategy SelectionCode0
Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-ConcatenationCode0
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision TransformersCode0
BERT-LSH: Reducing Absolute Compute For AttentionCode0
Show:102550
← PrevPage 172 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified