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 676–700 of 4891 papers

TitleStatusHype
Token Shift Transformer for Video ClassificationCode1
Multi-scale Matching Networks for Semantic CorrespondenceCode1
Learning Span-Level Interactions for Aspect Sentiment Triplet ExtractionCode1
Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare SettingsCode1
Adaptive wavelet distillation from neural networks through interpretationsCode1
Transformer-based Machine Learning for Fast SAT Solvers and Logic SynthesisCode1
Training Adaptive Computation for Open-Domain Question Answering with Computational ConstraintsCode1
DnS: Distill-and-Select for Efficient and Accurate Video Indexing and RetrievalCode1
Obtaining Better Static Word Embeddings Using Contextual Embedding ModelsCode1
Sub-Character Tokenization for Chinese Pretrained Language ModelsCode1
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image RecognitionCode1
A framework for data-driven solution and parameter estimation of PDEs using conditional generative adversarial networksCode1
Vision Transformer for Fast and Efficient Scene Text RecognitionCode1
Boosting Light-Weight Depth Estimation Via Knowledge DistillationCode1
Auction-Based Combinatorial Multi-Armed Bandit Mechanisms with Strategic ArmsCode1
Facial Emotion Recognition: State of the Art Performance on FER2013Code1
Adaptive Focus for Efficient Video RecognitionCode1
UVStyle-Net: Unsupervised Few-shot Learning of 3D Style Similarity Measure for B-RepsCode1
The 5th AI City ChallengeCode1
Consistent Accelerated Inference via Confident Adaptive TransformersCode1
Pyramidal Reservoir Graph Neural NetworkCode1
CondenseNet V2: Sparse Feature Reactivation for Deep NetworksCode1
Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and RegularizationCode1
Checkerboard Context Model for Efficient Learned Image CompressionCode1
Deep Implicit Moving Least-Squares Functions for 3D ReconstructionCode1
Show:102550
← PrevPage 28 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified