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 601–610 of 4891 papers

TitleStatusHype
A Transformer-based Framework for Multivariate Time Series Representation LearningCode1
InRank: Incremental Low-Rank LearningCode1
Boosting Light-Weight Depth Estimation Via Knowledge DistillationCode1
Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document EmbeddingsCode1
Content-aware Token Sharing for Efficient Semantic Segmentation with Vision TransformersCode1
GMSR:Gradient-Guided Mamba for Spectral Reconstruction from RGB ImagesCode1
Mixed Models with Multiple Instance LearningCode1
Contrast-Phys+: Unsupervised and Weakly-supervised Video-based Remote Physiological Measurement via Spatiotemporal ContrastCode1
Cross-attention Inspired Selective State Space Models for Target Sound ExtractionCode1
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsCode1
Show:102550
← PrevPage 61 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified