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 101–125 of 4891 papers

TitleStatusHype
Latent Neural Operator for Solving Forward and Inverse PDE ProblemsCode2
LeYOLO, New Scalable and Efficient CNN Architecture for Object DetectionCode2
Agent Attention: On the Integration of Softmax and Linear AttentionCode2
I^2-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene ForecastingCode2
LandMarkSystem Technical ReportCode2
Large Scale Longitudinal Experiments: Estimation and InferenceCode2
Balancing LoRA Performance and Efficiency with Simple Shard SharingCode2
BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV CacheCode2
A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint SpaceCode2
A Closer Look into Mixture-of-Experts in Large Language ModelsCode2
Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene RepresentationCode2
Integrating Neural Operators with Diffusion Models Improves Spectral Representation in Turbulence ModelingCode2
Harder Tasks Need More Experts: Dynamic Routing in MoE ModelsCode2
2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image ClassificationCode2
Long Context is Not Long at All: A Prospector of Long-Dependency Data for Large Language ModelsCode2
LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image RestorationCode2
HeadInfer: Memory-Efficient LLM Inference by Head-wise OffloadingCode2
Grappa -- A Machine Learned Molecular Mechanics Force FieldCode2
CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive SurveyCode2
MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable AutoencodersCode2
ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language ModelsCode2
InteractRank: Personalized Web-Scale Search Pre-Ranking with Cross Interaction FeaturesCode2
Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware SparsityCode2
LHU-Net: A Light Hybrid U-Net for Cost-Efficient, High-Performance Volumetric Medical Image SegmentationCode2
Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-ResolutionCode2
Show:102550
← PrevPage 5 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified