SOTAVerified

Memorization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1001–1050 of 1088 papers

TitleStatusHype
MILD: Modeling the Instance Learning Dynamics for Learning with Noisy LabelsCode0
Continual Referring Expression Comprehension via Dual Modular MemorizationCode0
Continual Dialogue State Tracking via Example-Guided Question AnsweringCode0
Minimum Description Length Hopfield NetworksCode0
Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language ModelsCode0
Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial TrainingCode0
Mitigating Label Noise through Data AmbiguationCode0
FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy LabelsCode0
Conditionally Strongly Log-Concave Generative ModelsCode0
Membership Inference Attacks are Easier on Difficult ProblemsCode0
How Spurious Features Are Memorized: Precise Analysis for Random and NTK FeaturesCode0
A Closer Look at Memorization in Deep NetworksCode0
Extreme Memorization via Scale of InitializationCode0
Redistribute Ensemble Training for Mitigating Memorization in Diffusion ModelsCode0
Reducing Training Sample Memorization in GANs by Training with Memorization RejectionCode0
Wide & Deep Learning for Node ClassificationCode0
Exploring Model Dynamics for Accumulative Poisoning DiscoveryCode0
MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGICode0
Model Editing for LLMs4Code: How Far are We?Code0
Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled MembershipsCode0
Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt TuningCode0
A mean teacher algorithm for unlearning of language modelsCode0
The Mosaic Memory of Large Language ModelsCode0
RELICT: A Replica Detection Framework for Medical Image GenerationCode0
Unmasking the Veil: An Investigation into Concept Ablation for Privacy and Copyright Protection in ImagesCode0
Evaluating LLMs for Quotation Attribution in Literary Texts: A Case Study of LLaMa3Code0
Muddling Label Regularization: Deep Learning for Tabular DatasetsCode0
Excess Capacity and Backdoor PoisoningCode0
RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationCode0
Evaluating and Explaining Natural Language Generation with GenXCode0
Enhancing elusive clues in knowledge learning by contrasting attention of language modelsCode0
Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language ModelsCode0
Emergent LLM behaviors are observationally equivalent to data leakageCode0
Negotiated Representations for Machine Mearning ApplicationCode0
A Probabilistic Fluctuation based Membership Inference Attack for Diffusion ModelsCode0
Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward LayersCode0
Toward a Generalization Metric for Deep Generative ModelsCode0
Neural Machine Translation in Linear TimeCode0
Sudoku-Bench: Evaluating creative reasoning with Sudoku variantsCode0
Response: Emergent analogical reasoning in large language modelsCode0
Neural Representations Reveal Distinct Modes of Class Fitting in Residual Convolutional NetworksCode0
Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language ModelsCode0
Asymptotic theory of in-context learning by linear attentionCode0
Classifier-Free Guidance inside the Attraction Basin May Cause MemorizationCode0
Noisy Concurrent Training for Efficient Learning under Label NoiseCode0
An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and CalibrationCode0
Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNsCode0
Unsupervised Text Embedding Space Generation Using Generative Adversarial Networks for Text SynthesisCode0
Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language ModelsCode0
Towards Clean-Label Backdoor Attacks in the Physical WorldCode0
Show:102550
← PrevPage 21 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