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 751–800 of 4891 papers

TitleStatusHype
DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference AccelerationCode1
Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent CodingCode1
Open-RadVLAD: Fast and Robust Radar Place RecognitionCode1
Cross-attention Inspired Selective State Space Models for Target Sound ExtractionCode1
Cross-Modality Multi-Atlas Segmentation via Deep Registration and Label FusionCode1
DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable LearnersCode1
Correlation Filters for Unmanned Aerial Vehicle-Based Aerial Tracking: A Review and Experimental EvaluationCode1
Overcoming Multi-Model Forgetting in One-Shot NAS With Diversity MaximizationCode1
ARNN: Attentive Recurrent Neural Network for Multi-channel EEG Signals to Identify Epileptic SeizuresCode1
CosmoPower-JAX: high-dimensional Bayesian inference with differentiable cosmological emulatorsCode1
PATS: Process-Level Adaptive Thinking Mode SwitchingCode1
Contrast-Phys+: Unsupervised and Weakly-supervised Video-based Remote Physiological Measurement via Spatiotemporal ContrastCode1
Corner Proposal Network for Anchor-free, Two-stage Object DetectionCode1
PointNorm: Dual Normalization is All You Need for Point Cloud AnalysisCode1
CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal ControlCode1
PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility GraphCode1
Content-aware Token Sharing for Efficient Semantic Segmentation with Vision TransformersCode1
A framework for data-driven solution and parameter estimation of PDEs using conditional generative adversarial networksCode1
Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNNCode1
Principal Uncertainty Quantification with Spatial Correlation for Image Restoration ProblemsCode1
Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document EmbeddingsCode1
Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM InferenceCode1
A Reverse Mamba Attention Network for Pathological Liver SegmentationCode1
PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement LearningCode1
Automated Lane Merging via Game Theory and Branch Model Predictive ControlCode1
Pyramidal Reservoir Graph Neural NetworkCode1
Consistent Accelerated Inference via Confident Adaptive TransformersCode1
Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained EnvironmentsCode1
Continual Learning For On-Device Environmental Sound ClassificationCode1
Learning Hierarchical Image Segmentation For Recognition and By RecognitionCode1
RANG: A Residual-based Adaptive Node Generation Method for Physics-Informed Neural NetworksCode1
A Flexible 2.5D Medical Image Segmentation Approach with In-Slice and Cross-Slice AttentionCode1
CondenseNet V2: Sparse Feature Reactivation for Deep NetworksCode1
Boosting Light-Weight Depth Estimation Via Knowledge DistillationCode1
An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP TasksCode1
CAMP: Collaborative Attention Model with Profiles for Vehicle Routing ProblemsCode1
Adaptive wavelet distillation from neural networks through interpretationsCode1
Reconstructing Compact Building Models from Point Clouds Using Deep Implicit FieldsCode1
Reduced Order Modeling with Shallow Recurrent Decoder NetworksCode1
Spatial and Spatial-Spectral Morphological Mamba for Hyperspectral Image ClassificationCode1
CE-SSL: Computation-Efficient Semi-Supervised Learning for ECG-based Cardiovascular Diseases DetectionCode1
Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)Code1
Resurrecting Recurrent Neural Networks for Long SequencesCode1
Rethinking Chain-of-Thought from the Perspective of Self-TrainingCode1
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential InformationCode1
Rethinking the Inception Architecture for Computer VisionCode1
Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation LearningCode1
PrimeK-Net: Multi-scale Spectral Learning via Group Prime-Kernel Convolutional Neural Networks for Single Channel Speech EnhancementCode1
Architectural Fusion Through Contextual Partitioning in Large Language Models: A Novel Approach to Parameterized Knowledge Integration—0
Architecting Digital Twins for Intelligent Transportation Systems—0
Show:102550
← PrevPage 16 of 98Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified