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 101–150 of 4891 papers

TitleStatusHype
MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable AutoencodersCode2
Multi-Modal Mamba Modeling for Survival Prediction (M4Survive): Adapting Joint Foundation Model RepresentationsCode2
LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image RestorationCode2
Long Context is Not Long at All: A Prospector of Long-Dependency Data for Large Language ModelsCode2
Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data RestorationCode2
Mixture of A Million ExpertsCode2
CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive SurveyCode2
ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language ModelsCode2
MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation ModelsCode2
A Closer Look into Mixture-of-Experts in Large Language ModelsCode2
LoRA-Pro: Are Low-Rank Adapters Properly Optimized?Code2
Many-MobileNet: Multi-Model Augmentation for Robust Retinal Disease ClassificationCode2
BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV CacheCode2
2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image ClassificationCode2
Balancing LoRA Performance and Efficiency with Simple Shard SharingCode2
Adaptive Multi-Scale Decomposition Framework for Time Series ForecastingCode2
Outlier-robust Kalman Filtering through Generalised BayesCode2
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts LayerCode2
Retinexmamba: Retinex-based Mamba for Low-light Image EnhancementCode2
Learning local equivariant representations for quantum operatorsCode2
BEBLID: Boosted efficient binary local image descriptorCode2
LEGNet: Lightweight Edge-Gaussian Driven Network for Low-Quality Remote Sensing Image Object DetectionCode2
Latent Neural Operator for Solving Forward and Inverse PDE ProblemsCode2
ConvMAE: Masked Convolution Meets Masked AutoencodersCode2
L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial AttacksCode2
Real-Time Polygonal Semantic Mapping for Humanoid Robot Stair ClimbingCode2
LeYOLO, New Scalable and Efficient CNN Architecture for Object DetectionCode2
LandMarkSystem Technical ReportCode2
L4acados: Learning-based models for acados, applied to Gaussian process-based predictive controlCode2
Large Scale Longitudinal Experiments: Estimation and InferenceCode2
InteractRank: Personalized Web-Scale Search Pre-Ranking with Cross Interaction FeaturesCode2
Integrating Neural Operators with Diffusion Models Improves Spectral Representation in Turbulence ModelingCode2
Latent Modulated Function for Computational Optimal Continuous Image RepresentationCode2
LHU-Net: A Light Hybrid U-Net for Cost-Efficient, High-Performance Volumetric Medical Image SegmentationCode2
Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene RepresentationCode2
Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing DetectionCode2
Accelerating Direct Preference Optimization with Prefix SharingCode2
Harder Tasks Need More Experts: Dynamic Routing in MoE ModelsCode2
A Survey on Diffusion Models for Anomaly DetectionCode2
HeadInfer: Memory-Efficient LLM Inference by Head-wise OffloadingCode2
I^2-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene ForecastingCode2
LightGNN: Simple Graph Neural Network for RecommendationCode2
A Simple Baseline for Efficient Hand Mesh ReconstructionCode2
GotenNet: Rethinking Efficient 3D Equivariant Graph Neural NetworksCode2
An Unforgeable Publicly Verifiable Watermark for Large Language ModelsCode2
Geometry Aware Operator Transformer as an Efficient and Accurate Neural Surrogate for PDEs on Arbitrary DomainsCode2
GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-MeshCode2
SparseLLM: Towards Global Pruning for Pre-trained Language ModelsCode2
Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMsCode2
Flow Matching in Latent SpaceCode2
Show:102550
← PrevPage 3 of 98Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified