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 1441–1450 of 4891 papers

TitleStatusHype
ActiveInitSplat: How Active Image Selection Helps Gaussian Splatting—0
Just Functioning as a Hook for Two-Stage Referring Multi-Object Tracking—0
LatexBlend: Scaling Multi-concept Customized Generation with Latent Textual Blending—0
Seesaw: High-throughput LLM Inference via Model Re-sharding—0
Joint Location and Velocity Estimation and Fundamental CRLB Analysis for Cell-Free MIMO-ISAC—0
Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs—0
InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models—0
Small Vision-Language Models: A Survey on Compact Architectures and Techniques—0
VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token EncodingsCode0
Steerable Pyramid Weighted Loss: Multi-Scale Adaptive Weighting for Semantic Segmentation—0
Show:102550
← PrevPage 145 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified