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 151–175 of 4891 papers

TitleStatusHype
Multi-Modal Mamba Modeling for Survival Prediction (M4Survive): Adapting Joint Foundation Model RepresentationsCode2
HeadInfer: Memory-Efficient LLM Inference by Head-wise OffloadingCode2
Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing DetectionCode2
Adaptive Multi-Scale Decomposition Framework for Time Series ForecastingCode2
Harder Tasks Need More Experts: Dynamic Routing in MoE ModelsCode2
AdaFisher: Adaptive Second Order Optimization via Fisher InformationCode2
Grappa -- A Machine Learned Molecular Mechanics Force FieldCode2
SparseLLM: Towards Global Pruning for Pre-trained Language ModelsCode2
A Survey on Diffusion Models for Anomaly DetectionCode2
Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene RepresentationCode2
A Simple Baseline for Efficient Hand Mesh ReconstructionCode2
Geometry Aware Operator Transformer as an Efficient and Accurate Neural Surrogate for PDEs on Arbitrary DomainsCode2
LandMarkSystem Technical ReportCode2
Large Scale Longitudinal Experiments: Estimation and InferenceCode2
Accelerating Direct Preference Optimization with Prefix SharingCode2
Latent Neural Operator for Solving Forward and Inverse PDE ProblemsCode2
GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-MeshCode2
An Unforgeable Publicly Verifiable Watermark for Large Language ModelsCode2
FuXi Weather: A data-to-forecast machine learning system for global weatherCode2
LightGNN: Simple Graph Neural Network for RecommendationCode2
Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-ResolutionCode2
GotenNet: Rethinking Efficient 3D Equivariant Graph Neural NetworksCode2
Balancing LoRA Performance and Efficiency with Simple Shard SharingCode2
LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image RestorationCode2
Flow Matching in Latent SpaceCode2
Show:102550
← PrevPage 7 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified