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 771–780 of 4891 papers

TitleStatusHype
Improved Techniques for Training Adaptive Deep NetworksCode1
FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective PropagationCode1
FastMap: Fast Queries Initialization Based Vectorized HD Map Reconstruction FrameworkCode1
Shallow Recurrent Decoder for Reduced Order Modeling of Plasma DynamicsCode1
Automated Lane Merging via Game Theory and Branch Model Predictive ControlCode1
Fast Point TransformerCode1
Cached Multi-Lora Composition for Multi-Concept Image GenerationCode1
Fast Sequence Based Embedding with Diffusion GraphsCode1
A Flexible 2.5D Medical Image Segmentation Approach with In-Slice and Cross-Slice AttentionCode1
DiMoSR: Feature Modulation via Multi-Branch Dilated Convolutions for Efficient Image Super-ResolutionCode1
Show:102550
← PrevPage 78 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified