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 2951–2975 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
Show:102550
← PrevPage 119 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified