| Minimum Description Length Hopfield Networks | Nov 11, 2023 | MemorizationRetrieval | CodeCode Available | 0 |
| Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models | Nov 10, 2023 | GSM8KMemorization | CodeCode Available | 1 |
| Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration | Nov 10, 2023 | Inference AttackMembership Inference Attack | CodeCode Available | 2 |
| Data Factors for Better Compositional Generalization | Nov 8, 2023 | DiagnosticMemorization | CodeCode Available | 0 |
| Preserving Privacy in GANs Against Membership Inference Attack | Nov 6, 2023 | Inference AttackMembership Inference Attack | —Unverified | 0 |
| From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models | Nov 4, 2023 | Backdoor Attackbackdoor defense | CodeCode Available | 0 |
| DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models | Oct 31, 2023 | MemorizationModel Editing | CodeCode Available | 1 |
| Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks | Oct 30, 2023 | Image ClassificationMemorization | CodeCode Available | 0 |
| The statistical thermodynamics of generative diffusion models: Phase transitions, symmetry breaking and critical instability | Oct 26, 2023 | MemorizationVariational Inference | —Unverified | 0 |
| Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding | Oct 25, 2023 | Memorization | —Unverified | 0 |
