SOTAVerified

Memorization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 751–800 of 1088 papers

TitleStatusHype
Local Feature Swapping for Generalization in Reinforcement Learning—0
PaLM: Scaling Language Modeling with PathwaysCode2
Towards Differential Relational Privacy and its use in Question Answering—0
UNICON: Combating Label Noise Through Uniform Selection and Contrastive LearningCode1
An Empirical Study of Memorization in NLPCode1
Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation—0
On the Generalization Mystery in Deep Learning—0
Euler State Networks: Non-dissipative Reservoir ComputingCode1
Data Contamination: From Memorization to ExploitationCode0
Do Language Models Plagiarize?Code1
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks—0
On Learning Contrastive Representations for Learning with Noisy LabelsCode1
KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models—0
Memory Planning for Deep Neural Networks—0
Quantifying Memorization Across Neural Language ModelsCode2
Membership Inference Attacks and Defenses in Neural Network PruningCode1
Do We Need to Penalize Variance of Losses for Learning with Label Noise?—0
Collaborative Learning in General Graphs with Limited Memorization: Complexity, Learnability, and Reliability—0
Universal Online Learning with Unbounded Losses: Memory Is All You Need—0
Towards Adversarial Evaluations for Inexact Machine UnlearningCode1
Provably Confidential Language Modelling—0
Quantifying Adaptability in Pre-trained Language Models with 500 Tasks—0
Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models—0
Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks—0
Universal Online Learning: an Optimistically Universal Learning Rule—0
Reasoning Through Memorization: Nearest Neighbor Knowledge Graph EmbeddingsCode1
Reconstructing Training Data with Informed AdversariesCode1
Grokking: Generalization Beyond Overfitting on Small Algorithmic DatasetsCode4
Semantics-Preserved Distortion for Personal Privacy Protection in Information Management—0
Learning With Twin Noisy Labels for Visible-Infrared Person Re-IdentificationCode1
Counterfactual Memorization in Neural Language Models—0
Economics of Innovation and Perceptions of Renewed Education and Curriculum Design in Bangladesh—0
Learning Positional Embeddings for Coordinate-MLPs—0
Evidentiality-guided Generation for Knowledge-Intensive NLP TasksCode1
Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation—0
Scaling Language Models: Methods, Analysis & Insights from Training GopherCode2
Quantifying Adaptability in Pre-trained Language Models with 500 TasksCode1
SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learning—0
Learning with Noisy Correspondence for Cross-modal MatchingCode1
On Memorization in Probabilistic Deep Generative ModelsCode0
ModelPred: A Framework for Predicting Trained Model from Training DataCode0
FFNB: Forgetting-Free Neural Blocks for Deep Continual Visual Learning—0
Enhanced Membership Inference Attacks against Machine Learning Models—0
Personalized Federated Learning through Local MemorizationCode1
Data Contamination: From Memorization to Exploitation—0
LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification—0
Regularising Fisher Information Improves Cross-lingual Generalisation—0
Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers—0
Learning with Noisy Labels Revisited: A Study Using Real-World Human AnnotationsCode1
Challenges in Procedural Multimodal Machine Comprehension:A Novel Way To Benchmark—0
Show:102550
← PrevPage 16 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