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 551–575 of 4891 papers

TitleStatusHype
Revisiting Funnel Transformers for Modern LLM Architectures with Comprehensive Ablations in Training and Inference Configurations—0
LLMPi: Optimizing LLMs for High-Throughput on Raspberry Pi—0
Test-time Adaptation for Foundation Medical Segmentation Model without Parametric Updates—0
Overcoming Vocabulary Constraints with Pixel-level Fallback—0
Robust Channel Estimation for Optical Wireless Communications Using Neural NetworkCode0
SpikeSift: A Computationally Efficient and Drift-Resilient Spike Sorting Algorithm—0
3D Gaussian Inverse Rendering with Approximated Global Illumination—0
Is Temporal Prompting All We Need For Limited Labeled Action Recognition?—0
An Explainable Reconfiguration-Based Optimization Algorithm for Industrial and Reliability-Redundancy Allocation Problems—0
ToolACE-R: Tool Learning with Adaptive Self-Refinement—0
Representing Flow Fields with Divergence-Free Kernels for Reconstruction—0
FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generation—0
UniViTAR: Unified Vision Transformer with Native Resolution—0
FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learning—0
High Dimensional Bayesian Optimization using Lasso Variable SelectionCode0
CFMD: Dynamic Cross-layer Feature Fusion for Salient Object Detection—0
Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries—0
SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching—0
Benchmarking Federated Machine Unlearning methods for Tabular Data—0
MetaLoRA: Tensor-Enhanced Adaptive Low-Rank Fine-tuning—0
FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization—0
Dynamic Graph Structure Estimation for Learning Multivariate Point Process using Spiking Neural Networks—0
Efficient n-body simulations using physics informed graph neural networks—0
Learning-Based Approximate Nonlinear Model Predictive Control Motion Cueing—0
GLiNER-BioMed: A Suite of Efficient Models for Open Biomedical Named Entity RecognitionCode1
Show:102550
← PrevPage 23 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified