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 1561–1570 of 4891 papers

TitleStatusHype
DST-TransitNet: A Dynamic Spatio-Temporal Deep Learning Model for Scalable and Efficient Network-Wide Prediction of Station-Level Transit Ridership—0
Advancing Physics Data Analysis through Machine Learning and Physics-Informed Neural Networks—0
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling—0
Combining Entropy and Matrix Nuclear Norm for Enhanced Evaluation of Language Models—0
Learning to Control the Smoothness of Graph Convolutional Network Features—0
Tensor Decomposition with Unaligned Observations—0
FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion ModelCode3
Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers—0
Learning Efficient Representations of Neutrino Telescope EventsCode0
Quamba: A Post-Training Quantization Recipe for Selective State Space ModelsCode2
Show:102550
← PrevPage 157 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified