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 826–850 of 4891 papers

TitleStatusHype
Transported Memory Networks accelerating Computational Fluid Dynamics—0
Tukey Depth Mechanisms for Practical Private Mean Estimation—0
Recurrent Neural Networks for Dynamic VWAP Execution: Adaptive Trading Strategies with Temporal Kolmogorov-Arnold NetworksCode0
Optimal Brain ApoptosisCode0
InVDriver: Intra-Instance Aware Vectorized Query-Based Autonomous Driving Transformer—0
VesselSAM: Leveraging SAM for Aortic Vessel Segmentation with AtrousLoRACode1
Design and implementation of a distributed security threat detection system integrating federated learning and multimodal LLM—0
Architecting Digital Twins for Intelligent Transportation Systems—0
Learning Backbones: Sparsifying Graphs through Zero Forcing for Effective Graph-Based Learning—0
Random Projections and Natural Sparsity in Time-Series Classification: A Theoretical Analysis—0
Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical SystemsCode2
Muon is Scalable for LLM TrainingCode7
Agentic AI for Behavior-Driven Development Testing Using Large Language ModelsCode0
End-to-End Deep Learning for Structural Brain Imaging: A Unified FrameworkCode0
A Reverse Mamba Attention Network for Pathological Liver SegmentationCode1
DISC: DISC: Dynamic Decomposition Improves LLM Inference Scaling—0
A strictly predefined-time convergent and anti-noise fractional-order zeroing neural network for solving time-variant quadratic programming in kinematic robot control—0
Pseudo-Measurement Enhancement in Power Distribution Systems—0
Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery—0
Graph Self-Supervised Learning with Learnable Structural and Positional EncodingsCode0
MOB-GCN: A Novel Multiscale Object-Based Graph Neural Network for Hyperspectral Image ClassificationCode0
Dynamic Parallel Tree Search for Efficient LLM Reasoning—0
TabMixer: advancing tabular data analysis with an enhanced MLP-mixer approachCode1
Hard constraint learning approaches with trainable influence functions for evolutionary equationsCode0
Probabilistic Formulations for System Identification of Linear Dynamics with Bilinear Observation Models—0
Show:102550
← PrevPage 34 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified