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 2576–2600 of 4891 papers

TitleStatusHype
Guaranteed Trust Region Optimization via Two-Phase KL Penalization—0
Accelerating Convolutional Neural Network Pruning via Spatial Aura Entropy—0
GenQ: Quantization in Low Data Regimes with Generative Synthetic DataCode0
Deep Dynamics: Vehicle Dynamics Modeling with a Physics-Constrained Neural Network for Autonomous Racing—0
Efficiently Predicting Protein Stability Changes Upon Single-point Mutation with Large Language Models—0
Learning to sample in Cartesian MRI—0
Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization ApproachCode1
Time-Domain Operational Metrics for Real-time Resilience Assessment in DC Microgrids—0
Differentiable Point-based Inverse Rendering—0
SchurVINS: Schur Complement-Based Lightweight Visual Inertial Navigation SystemCode2
PLUM: Improving Inference Efficiency By Leveraging Repetition-Sparsity Trade-OffCode0
Divide-and-Conquer Strategy for Large-Scale Dynamic Bayesian Network Structure Learning—0
Foundations for Transfer in Reinforcement Learning: A Taxonomy of Knowledge Modalities—0
On Significance of Subword tokenization for Low Resource and Efficient Named Entity Recognition: A case study in Marathi—0
Token Fusion: Bridging the Gap between Token Pruning and Token Merging—0
Feature Aggregating Network with Inter-Frame Interaction for Efficient Video Super-Resolution—0
Mamba: Linear-Time Sequence Modeling with Selective State SpacesCode6
Subspace Hybrid MVDR Beamforming for Augmented Hearing—0
TransNAS-TSAD: Harnessing Transformers for Multi-Objective Neural Architecture Search in Time Series Anomaly DetectionCode0
LayerCollapse: Adaptive compression of neural networks—0
SAIBench: A Structural Interpretation of AI for Science Through Benchmarks—0
U-Net v2: Rethinking the Skip Connections of U-Net for Medical Image SegmentationCode6
MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices—0
FakeWatch ElectionShield: A Benchmarking Framework to Detect Fake News for Credible US Elections—0
Spatially Adaptive Cloth Regression with Implicit Neural Representations—0
Show:102550
← PrevPage 104 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified