SOTAVerified

Memorization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 901–950 of 1088 papers

TitleStatusHype
On the Robustness of Monte Carlo Dropout Trained with Noisy Labels—0
Privacy Regularization: Joint Privacy-Utility Optimization in Language Models—0
On the privacy-utility trade-off in differentially private hierarchical text classificationCode0
Parsimonious Inference—0
Membership Inference Attacks are Easier on Difficult ProblemsCode0
Robust Generalization and Safe Query-Specialization in Counterfactual Learning to RankCode0
Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance EvaluationCode0
Learning to Combat Noisy Labels via Classification Margins—0
Meta-Regularization by Enforcing Mutual-ExclusivenessCode0
PConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network—0
Investigating Memorization of Conspiracy Theories in Text GenerationCode0
The Unreasonable Effectiveness of the Class-reversed Sampling in Tail Sample Memorization—0
ME-MOMENTUM: EXTRACTING HARD CONFIDENT EXAMPLES FROM NOISILY LABELED DATA—0
Distributed Associative Memory Network with Association Reinforcing Loss—0
Catching the Long Tail in Deep Neural Networks—0
A Large-scale Study on Training Sample Memorization in Generative Modeling—0
Making Coherence Out of Nothing At All: Measuring Evolution of Gradient Alignment—0
Robust early-learning: Hindering the memorization of noisy labels—0
Continual Memory: Can We Reason After Long-Term Memorization?—0
How Do Your Biomedical Named Entity Recognition Models Generalize to Novel Entities?Code0
Introducing Orthogonal Constraint in Structural ProbesCode0
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization—0
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks—0
Perceptron Theory Can Predict the Accuracy of Neural Networks—0
When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?Code0
A Bayesian Nonparametrics View into Deep Representations—0
Modifying Memories in Transformer Models—0
Network size and size of the weights in memorization with two-layers neural networks—0
Generalization and Memorization: The Bias Potential Model—0
Cross-Domain Generalization Through Memorization: A Study of Nearest Neighbors in Neural Duplicate Question Detection—0
Power System Event Identification based on Deep Neural Network with Information Loading—0
Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based InitializationCode0
Toward a Generalization Metric for Deep Generative ModelsCode0
Provable Memorization via Deep Neural Networks using Sub-linear Parameters—0
Revisiting Explicit Regularization in Neural Networks for Reliable Predictive Probability—0
Training Production Language Models without Memorizing User Data—0
Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models—0
Noisy Concurrent Training for Efficient Learning under Label NoiseCode0
Extreme Memorization via Scale of InitializationCode0
Salvage Reusable Samples from Noisy Data for Robust LearningCode0
Making Coherence Out of Nothing At All: Measuring the Evolution of Gradient Alignment—0
The Interpolation Phase Transition in Neural Networks: Memorization and Generalization under Lazy Training—0
Bridging the Imitation Gap by Adaptive Insubordination—0
Multi-Sample Online Learning for Probabilistic Spiking Neural Networks—0
Distributed Associative Memory Network with Memory Refreshing LossCode0
Audio Tagging by Cross Filtering Noisy Labels—0
BiRRE: Learning Bidirectional Residual Relation Embeddings for Supervised Hypernymy Detection—0
Measuring Memorization Effect in Word-Level Neural Networks Probing—0
What they do when in doubt: a study of inductive biases in seq2seq learnersCode0
What Do Neural Networks Learn When Trained With Random Labels?—0
Show:102550
← PrevPage 19 of 22Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PaLM-540B (few-shot, k=5)Accuracy95.4—Unverified
2Gopher-280B (few-shot, k=5)Accuracy80—Unverified
3PaLM-62B (few-shot, k=5)Accuracy77.7—Unverified