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

Showing 181190 of 4891 papers

TitleStatusHype
vid-TLDR: Training Free Token merging for Light-weight Video TransformerCode2
Harder Tasks Need More Experts: Dynamic Routing in MoE ModelsCode2
RFWave: Multi-band Rectified Flow for Audio Waveform ReconstructionCode2
A Simple Baseline for Efficient Hand Mesh ReconstructionCode2
SparseLLM: Towards Global Pruning for Pre-trained Language ModelsCode2
Fast Adversarial Attacks on Language Models In One GPU MinuteCode2
VOOM: Robust Visual Object Odometry and Mapping using Hierarchical LandmarksCode2
Mercury: A Code Efficiency Benchmark for Code Large Language ModelsCode2
CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular FusionCode2
BEBLID: Boosted efficient binary local image descriptorCode2
Show:102550
← PrevPage 19 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05Unverified