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 1551–1575 of 4891 papers

TitleStatusHype
Practical Topics in Optimization—0
Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration PitfallsCode0
RemInD: Remembering Anatomical Variations for Interpretable Domain Adaptive Medical Image Segmentation—0
Probabilistic Lexical Manifold Construction in Large Language Models via Hierarchical Vector Field Interpolation—0
HADL Framework for Noise Resilient Long-Term Time Series ForecastingCode0
Rolling Ahead Diffusion for Traffic Scene Simulation—0
Long-Range LiDAR Vehicle Detection Through Clustering and Classification for Autonomous Racing—0
Linear-Time User-Level DP-SCO via Robust Statistics—0
Structured Convergence in Large Language Model Representations via Hierarchical Latent Space Folding—0
E-MD3C: Taming Masked Diffusion Transformers for Efficient Zero-Shot Object Customization—0
FLAME: Flexible LLM-Assisted Moderation Engine—0
Data-Enabled Predictive Control for Flexible Spacecraft—0
GoRA: Gradient-driven Adaptive Low Rank Adaptation—0
Criteria-Aware Graph Filtering: Extremely Fast Yet Accurate Multi-Criteria RecommendationCode0
Contextual Compression Encoding for Large Language Models: A Novel Framework for Multi-Layered Parameter Space Pruning—0
Recurrent Memory for Online Interdomain Gaussian Processes—0
TANTE: Time-Adaptive Operator Learning via Neural Taylor Expansion—0
The Paradox of Stochasticity: Limited Creativity and Computational Decoupling in Temperature-Varied LLM Outputs of Structured Fictional Data—0
Neuromorphic Digital-Twin-based Controller for Indoor Multi-UAV Systems Deployment—0
A Low-Complexity Plug-and-Play Deep Learning Model for Massive MIMO Precoding Across Sites—0
Low-Resolution Neural Networks—0
Fast-COS: A Fast One-Stage Object Detector Based on Reparameterized Attention Vision Transformer for Autonomous Driving—0
Provably Efficient RLHF Pipeline: A Unified View from Contextual Bandits—0
MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition—0
Filtered Markovian Projection: Dimensionality Reduction in Filtering for Stochastic Reaction NetworksCode0
Show:102550
← PrevPage 63 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified