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 3061–3070 of 4891 papers

TitleStatusHype
TPDiff: Temporal Pyramid Video Diffusion Model—0
TpopT: Efficient Trainable Template Optimization on Low-Dimensional Manifolds—0
TQ-DiT: Efficient Time-Aware Quantization for Diffusion Transformers—0
Tracking objects using 3D object proposals—0
Tractable Identification of Electric Distribution Networks—0
TRADI: Tracking deep neural network weight distributions for uncertainty estimation—0
TraIL-Det: Transformation-Invariant Local Feature Networks for 3D LiDAR Object Detection with Unsupervised Pre-Training—0
Training and inference of large language models using 8-bit floating point—0
Training Binary Weight Networks via Semi-Binary Decomposition—0
Training Energy-Efficient Deep Spiking Neural Networks with Single-Spike Hybrid Input Encoding—0
Show:102550
← PrevPage 307 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified