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 661–670 of 4891 papers

TitleStatusHype
Hyper-CL: Conditioning Sentence Representations with HypernetworksCode1
CryoAI: Amortized Inference of Poses for Ab Initio Reconstruction of 3D Molecular Volumes from Real Cryo-EM ImagesCode1
DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference AccelerationCode1
A Variational Infinite Mixture for Probabilistic Inverse Dynamics LearningCode1
A Walsh Hadamard Derived Linear Vector Symbolic ArchitectureCode1
AMD-Hummingbird: Towards an Efficient Text-to-Video ModelCode1
BetterNet: An Efficient CNN Architecture with Residual Learning and Attention for Precision Polyp SegmentationCode1
BabyAI 1.1Code1
Improving Computational Efficiency in Visual Reinforcement Learning via Stored EmbeddingsCode1
Cross-attention Inspired Selective State Space Models for Target Sound ExtractionCode1
Show:102550
← PrevPage 67 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified