| Next-token prediction capacity: general upper bounds and a lower bound for transformers | May 22, 2024 | DecoderMemorization | CodeCode Available | 0 |
| FINED: Feed Instance-Wise Information Need with Essential and Disentangled Parametric Knowledge from the Past | May 20, 2024 | DisentanglementMemorization | —Unverified | 0 |
| Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs | May 20, 2024 | DisentanglementLanguage Modeling | —Unverified | 0 |
| Asymptotic theory of in-context learning by linear attention | May 20, 2024 | DiversityIn-Context Learning | CodeCode Available | 0 |
| A Multi-Perspective Analysis of Memorization in Large Language Models | May 19, 2024 | Memorization | —Unverified | 0 |
| Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective | May 17, 2024 | Backdoor AttackMemorization | CodeCode Available | 1 |
| Learnable Privacy Neurons Localization in Language Models | May 16, 2024 | MemorizationSpecificity | —Unverified | 0 |
| Generalized Holographic Reduced Representations | May 15, 2024 | Memorization | —Unverified | 0 |
| Dynamic Loss Decay based Robust Oriented Object Detection on Remote Sensing Images with Noisy Labels | May 15, 2024 | Memorizationobject-detection | —Unverified | 0 |
| Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory | May 14, 2024 | Memorization | —Unverified | 0 |
