SOTAVerified

Memorization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 301–350 of 1088 papers

TitleStatusHype
Autoencoder-based Initialization for Recurrent Neural Networks with a Linear Memory—0
A Corrective View of Neural Networks: Representation, Memorization and Learning—0
CopyrightShield: Spatial Similarity Guided Backdoor Defense against Copyright Infringement in Diffusion Models—0
CopyJudge: Automated Copyright Infringement Identification and Mitigation in Text-to-Image Diffusion Models—0
Audio Tagging by Cross Filtering Noisy Labels—0
A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference Information—0
Historical Test-time Prompt Tuning for Vision Foundation Models—0
Continuous Reinforcement Learning-based Dynamic Difficulty Adjustment in a Visual Working Memory Game—0
A Mathematical Framework for Learning Probability Distributions—0
Attention Beats Concatenation for Conditioning Neural Fields—0
Continual Memory: Can We Reason After Long-Term Memorization?—0
Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding—0
Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers—0
Continual Learning Should Move Beyond Incremental Classification—0
Asynchronous Personalized Federated Learning through Global Memorization—0
Context-based Virtual Adversarial Training for Text Classification with Noisy Labels—0
Data-centric NLP Backdoor Defense from the Lens of Memorization—0
FFNB: Forgetting-Free Neural Blocks for Deep Continual Visual Learning—0
Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorization—0
ALTBI: Constructing Improved Outlier Detection Models via Optimization of Inlier-Memorization Effect—0
Confidence Adaptive Regularization for Deep Learning with Noisy Labels—0
GP-MoLFormer: A Foundation Model For Molecular Generation—0
Graph Memory Learning: Imitating Lifelong Remembering and Forgetting of Brain Networks—0
Geometry of Neural Network Loss Surfaces via Random Matrix Theory—0
Computation with Sequences in a Model of the Brain—0
Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization—0
Compositional Generalization Requires More Than Disentangled Representations—0
Extreme Image Transformations Facilitate Robust Latent Object Representations—0
Extracting Unlearned Information from LLMs with Activation Steering—0
A Comparative Study of Reservoir Computing for Temporal Signal Processing—0
Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective—0
Extracting Training Data from Unconditional Diffusion Models—0
Extracting Training Data from Document-Based VQA Models—0
Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers—0
Extracting memorized pieces of (copyrighted) books from open-weight language models—0
FINED: Feed Instance-Wise Information Need with Essential and Disentangled Parametric Knowledge from the Past—0
Assessing Generalization in TD methods for Deep Reinforcement Learning—0
Factored Agents: Decoupling In-Context Learning and Memorization for Robust Tool Use—0
A Spline Theory of Deep Learning—0
Fast Parametric Learning with Activation Memorization—0
Fault-Diagnosing SLAM for Varying Scale Change Detection—0
Assessing Intelligence in Artificial Neural Networks—0
Expressive Power of ReLU and Step Networks under Floating-Point Operations—0
Federated Nearest Neighbor Machine Translation—0
Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning—0
Few-Shot Generation of Brain Tumors for Secure and Fair Data Sharing—0
Combating Label Noise With A General Surrogate Model For Sample Selection—0
Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them—0
Co-matching: Combating Noisy Labels by Augmentation Anchoring—0
Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens—0
Show:102550
← PrevPage 7 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