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 551–560 of 4891 papers

TitleStatusHype
Revisiting Funnel Transformers for Modern LLM Architectures with Comprehensive Ablations in Training and Inference Configurations—0
Overcoming Vocabulary Constraints with Pixel-level Fallback—0
LLMPi: Optimizing LLMs for High-Throughput on Raspberry Pi—0
Test-time Adaptation for Foundation Medical Segmentation Model without Parametric Updates—0
Robust Channel Estimation for Optical Wireless Communications Using Neural NetworkCode0
FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learning—0
Is Temporal Prompting All We Need For Limited Labeled Action Recognition?—0
3D Gaussian Inverse Rendering with Approximated Global Illumination—0
An Explainable Reconfiguration-Based Optimization Algorithm for Industrial and Reliability-Redundancy Allocation Problems—0
FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generation—0
Show:102550
← PrevPage 56 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified