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

Showing 41514200 of 4891 papers

TitleStatusHype
Advancing Distributed AC Optimal Power Flow for Integrated Transmission-Distribution Systems0
Distributed Consensus Optimization with Consensus ALADIN0
Distributed Cross-Channel Hierarchical Aggregation for Foundation Models0
Distributed Differential Dynamic Programming Architectures for Large-Scale Multi-Agent Control0
Distributed Differentially Private Data Analytics via Secure Sketching0
Distributed Experiment Design and Control for Multi-agent Systems with Gaussian Processes0
Distributed Flexible Nonlinear Tensor Factorization0
Distributed Sketching Methods for Privacy Preserving Regression0
Distributed Traffic Signal Control via Coordinated Maximum Pressure-plus-Penalty0
Distributionally Robust Model Predictive Control with Total Variation Distance0
Distribution-Aware Sampling and Weighted Model Counting for SAT0
DITTO: Diffusion Inference-Time T-Optimization for Music Generation0
Diverse super-resolution with pretrained deep hiererarchical VAEs0
Divide-and-Conquer Strategy for Large-Scale Dynamic Bayesian Network Structure Learning0
Divide, Specialize, and Route: A New Approach to Efficient Ensemble Learning0
DLCM: a versatile multi-level solver for heterogeneous multicellular systems0
DMFC-GraspNet: Differentiable Multi-Fingered Robotic Grasp Generation in Cluttered Scenes0
DMRA: An Adaptive Line Spectrum Estimation Method through Dynamical Multi-Resolution of Atoms0
DNA cyclization and looping in the wormlike limit: normal modes and the validity of the harmonic approximation0
DNN-Compressed Domain Visual Recognition with Feature Adaptation0
DN-ResNet: Efficient Deep Residual Network for Image Denoising0
Do global forecasting models require frequent retraining?0
DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization0
Domain Adaptation Broad Learning System Based on Locally Linear Embedding0
Domain Adaptation Extreme Learning Machines for Drift Compensation in E-nose Systems0
Domain-Aware Few-Shot Learning for Optical Coherence Tomography Noise Reduction0
Domain-Specific Japanese ELECTRA Model Using a Small Corpus0
Don't Fall for Tuning Parameters: Tuning-Free Variable Selection in High Dimensions With the TREX0
Don't forget, there is more than forgetting: new metrics for Continual Learning0
Double Machine Learning for Adaptive Causal Representation in High-Dimensional Data0
Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables0
Do we become wiser with time? On causal equivalence with tiered background knowledge0
DP-CDA: An Algorithm for Enhanced Privacy Preservation in Dataset Synthesis Through Randomized Mixing0
DPERC: Direct Parameter Estimation for Mixed Data0
DP-LET: An Efficient Spatio-Temporal Network Traffic Prediction Framework0
DRACO: Co-Optimizing Hardware Utilization, and Performance of DNNs on Systolic Accelerator0
DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation0
DRL-based Dolph-Tschebyscheff Beamforming in Downlink Transmission for Mobile Users0
DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving0
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs0
DST-TransitNet: A Dynamic Spatio-Temporal Deep Learning Model for Scalable and Efficient Network-Wide Prediction of Station-Level Transit Ridership0
DS-VIO: Robust and Efficient Stereo Visual Inertial Odometry based on Dual Stage EKF0
DTFSal: Audio-Visual Dynamic Token Fusion for Video Saliency Prediction0
DTMNet: A Discrete Tchebichef Moments-Based Deep Neural Network for Multi-Focus Image Fusion0
Dual Conditional Diffusion Models for Sequential Recommendation0
Dual-control based approach to batch process operation under uncertainty based on optimality-conditions parameterization0
DualFL: A Duality-based Federated Learning Algorithm with Communication Acceleration in the General Convex Regime0
Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces0
Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization0
Dual optimization for convex constrained objectives without the gradient-Lipschitz assumption0
Show:102550
← PrevPage 84 of 98Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05Unverified