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
LEGNet: Lightweight Edge-Gaussian Driven Network for Low-Quality Remote Sensing Image Object DetectionCode2
Advances in 4D Generation: A SurveyCode2
ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language ModelsCode2
RoMA: Scaling up Mamba-based Foundation Models for Remote SensingCode2
Multi-Modal Mamba Modeling for Survival Prediction (M4Survive): Adapting Joint Foundation Model RepresentationsCode2
Emulating Self-attention with Convolution for Efficient Image Super-ResolutionCode2
Real-time Spatial-temporal Traversability Assessment via Feature-based Sparse Gaussian ProcessCode2
Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical SystemsCode2
Fast and Accurate Blind Flexible DockingCode2
MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable AutoencodersCode2
HeadInfer: Memory-Efficient LLM Inference by Head-wise OffloadingCode2
Without Paired Labeled Data: An End-to-End Self-Supervised Paradigm for UAV-View Geo-LocalizationCode2
Reviving The Classics: Active Reward Modeling in Large Language Model AlignmentCode2
Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware SparsityCode2
Uni-Sign: Toward Unified Sign Language Understanding at ScaleCode2
A Survey on Diffusion Models for Anomaly DetectionCode2
RWKV-UNet: Improving UNet with Long-Range Cooperation for Effective Medical Image SegmentationCode2
AlphaNet: Scaling Up Local-frame-based Atomistic Interatomic PotentialCode2
Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-ResolutionCode2
FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow MatchingCode2
LightGNN: Simple Graph Neural Network for RecommendationCode2
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language ModelsCode2
VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo AlignmentCode2
A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint SpaceCode2
The dark side of the forces: assessing non-conservative force models for atomistic machine learningCode2
Show:102550
← PrevPage 5 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified