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 1126–1150 of 4891 papers

TitleStatusHype
CodeVision: Detecting LLM-Generated Code Using 2D Token Probability Maps and Vision Models—0
Low-Order Flow Reconstruction and Uncertainty Quantification in Disturbed Aerodynamics Using Sparse Pressure MeasurementsCode0
LightGNN: Simple Graph Neural Network for RecommendationCode2
Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models—0
GraphDART: Graph Distillation for Efficient Advanced Persistent Threat Detection—0
CAMP: Collaborative Attention Model with Profiles for Vehicle Routing ProblemsCode1
KM-UNet KAN Mamba UNet for medical image segmentationCode1
The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit—0
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language ModelsCode2
Majorization-Minimization Dual Stagewise Algorithm for Generalized Lasso—0
Quaternionic Reweighted Amplitude Flow for Phase Retrieval in Image Reconstruction—0
Emergency-Brake Simplex: Toward A Verifiably Safe Control-CPS Architecture for Abrupt Runtime Reachability Constraint Changes—0
LCFed: An Efficient Clustered Federated Learning Framework for Heterogeneous Data—0
Tree-NET: Enhancing Medical Image Segmentation Through Efficient Low-Level Feature Training—0
Robust Self-Paced Hashing for Cross-Modal Retrieval with Noisy LabelsCode1
VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo AlignmentCode2
Task-Driven Fixation Network: An Efficient Architecture with Fixation Selection—0
Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models—0
Less is More: Efficient Image Vectorization with Adaptive Parameterization—0
Rethinking Token Reduction with Parameter-Efficient Fine-Tuning in ViT for Pixel-Level TasksCode0
ACL: Activating Capability of Linear Attention for Image Restoration—0
V2V3D: View-to-View Denoised 3D Reconstruction for Light Field Microscopy—0
GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections—0
Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning—0
One-Way Ticket: Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models—0
Show:102550
← PrevPage 46 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified