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 2951–3000 of 4891 papers

TitleStatusHype
Tazza: Shuffling Neural Network Parameters for Secure and Private Federated Learning—0
TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescription Prediction—0
TCM-GPT: Efficient Pre-training of Large Language Models for Domain Adaptation in Traditional Chinese Medicine—0
TDDBench: A Benchmark for Training data detection—0
Teacher Guided Architecture Search—0
Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint—0
Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning—0
Temporal-Coded Spiking Neural Networks with Dynamic Firing Threshold: Learning with Event-Driven Backpropagation—0
Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency—0
Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks—0
Temporal-Spatial Attention Network (TSAN) for DoS Attack Detection in Network Traffic—0
Tensor-Based Backpropagation in Neural Networks with Non-Sequential Input—0
Tensor Decomposition with Unaligned Observations—0
Low-rank Tensor Grid for Image Completion—0
TensorSocket: Shared Data Loading for Deep Learning Training—0
Test-time Adaptation for Foundation Medical Segmentation Model without Parametric Updates—0
TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes—0
Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching—0
The 4th AI City Challenge—0
The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph—0
The Chan-Vese Model with Elastica and Landmark Constraints for Image Segmentation—0
The Chronicles of RAG: The Retriever, the Chunk and the Generator—0
The column measure and Gradient-Free Gradient Boosting—0
The constrained Dantzig selector with enhanced consistency—0
The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit—0
The Globally Optimal Reparameterization Algorithm: an Alternative to Fast Dynamic Time Warping for Action Recognition in Video Sequences—0
The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases—0
The impact of imbalanced training data on machine learning for author name disambiguation—0
The Inhibitor: ReLU and Addition-Based Attention for Efficient Transformers—0
The jigsaw puzzle of sequence phenotype inference: Piecing together Shannon entropy, importance sampling, and Empirical Bayes—0
The k-Support Norm and Convex Envelopes of Cardinality and Rank—0
The Latent Road to Atoms: Backmapping Coarse-grained Protein Structures with Latent Diffusion—0
The mass-conversion method: a hybrid technique for simulating well-mixed chemical reaction networks—0
The Moral Case for Using Language Model Agents for Recommendation—0
The Morphology-Control Trade-Off: Insights into Soft Robotic Efficiency—0
The Need for Speed of AI Applications: Performance Comparison of Native vs. Browser-based Algorithm Implementations—0
The Open Source Advantage in Large Language Models (LLMs)—0
The Ordered Residual Kernel for Robust Motion Subspace Clustering—0
Theoretical Guarantees for LT-TTD: A Unified Transformer-based Architecture for Two-Level Ranking Systems—0
Theory of Mixture-of-Experts for Mobile Edge Computing—0
The Paradox of Stochasticity: Limited Creativity and Computational Decoupling in Temperature-Varied LLM Outputs of Structured Fictional Data—0
Encoder blind combinatorial compressed sensing—0
The Power of Complementary Regularizers: Image Recovery via Transform Learning and Low-Rank Modeling—0
The Power of Few: Accelerating and Enhancing Data Reweighting with Coreset Selection—0
The Power Of Simplicity: Why Simple Linear Models Outperform Complex Machine Learning Techniques -- Case Of Breast Cancer Diagnosis—0
The Quadrature Gaussian Sum Filter and Smoother for Wiener Systems—0
The Recycling Gibbs Sampler for Efficient Learning—0
The return of AdaBoost.MH: multi-class Hamming trees—0
Thermal Modelling of Battery Cells for Optimal Tab and Surface Cooling Control—0
The Role of Extended Horizon Methodology in Renewable-Dense Grids With Inter-Day Long-Duration Energy Storage—0
Show:102550
← PrevPage 60 of 98Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified