SOTAVerified

Memorization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 701–750 of 1088 papers

TitleStatusHype
Mitigating Unintended Memorization in Language Models via Alternating Teaching—0
FreGAN: Exploiting Frequency Components for Training GANs under Limited DataCode1
An associative memory model with very high memory rate: Image storage by sequential addition learning—0
Understanding Transformer Memorization Recall Through IdiomsCode1
Synthetic Dataset Generation for Privacy-Preserving Machine Learning—0
Attention Beats Concatenation for Conditioning Neural Fields—0
Small Transformers Compute Universal Metric EmbeddingsCode0
Data Isotopes for Data Provenance in DNNs—0
On the Privacy Effect of Data Enhancement via the Lens of MemorizationCode0
Visual Localization via Few-Shot Scene Region ClassificationCode1
LiDAR-based localization using universal encoding and memory-aware regressionCode0
Continual Variational Autoencoder Learning via Online Cooperative MemorizationCode1
Towards Better Evaluation for Dynamic Link PredictionCode1
Challenging Common Assumptions about Catastrophic Forgetting—0
Generalization-Memorization MachinesCode0
Does it Really Generalize Well on Unseen Data? Systematic Evaluation of Relational Triple Extraction Methods—0
Privacy Leakage in Text Classification A Data Extraction Approach—0
Training Text-to-Text Transformers with Privacy Guarantees—0
Measuring Forgetting of Memorized Training Examples—0
Towards Harnessing Feature Embedding for Robust Learning with Noisy Labels—0
The Privacy Onion Effect: Memorization is RelativeCode0
Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender BiasCode0
Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence—0
Memorization-Dilation: Modeling Neural Collapse Under Label NoiseCode0
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelsCode4
Privacy Leakage in Text Classification: A Data Extraction Approach—0
Learning to generate imaginary tasks for improving generalization in meta-learning—0
Large Loss Matters in Weakly Supervised Multi-Label ClassificationCode1
MSR: Making Self-supervised learning Robust to Aggressive Augmentations—0
White-box Membership Attack Against Machine Learning Based Retinopathy Classification—0
Context-based Virtual Adversarial Training for Text Classification with Noisy Labels—0
Decoupling Knowledge from Memorization: Retrieval-augmented Prompt LearningCode2
Are Large Pre-Trained Language Models Leaking Your Personal Information?Code1
LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text ClassificationCode0
Contrastive Learning with Boosted MemorizationCode1
Memorization in NLP Fine-tuning MethodsCode1
Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models—0
What Do Compressed Multilingual Machine Translation Models Forget?Code0
Scaling Laws and Interpretability of Learning from Repeated Data—0
Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization—0
Towards Understanding Grokking: An Effective Theory of Representation LearningCode1
AdaCap: Adaptive Capacity control for Feed-Forward Neural Networks—0
Affective Medical Estimation and Decision Making via Visualized Learning and Deep LearningCode0
Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt TuningCode0
Provably Confidential Language ModellingCode0
SELC: Self-Ensemble Label Correction Improves Learning with Noisy LabelsCode1
Mixup-based Deep Metric Learning Approaches for Incomplete Supervision—0
Detecting Unintended Memorization in Language-Model-Fused ASR—0
Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language ModelsCode0
Self-Guided Learning to Denoise for Robust RecommendationCode1
Show:102550
← PrevPage 15 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