| Captured by Captions: On Memorization and its Mitigation in CLIP Models | Feb 11, 2025 | Image RetrievalMemorization | —Unverified | 0 |
| The Devil is in the Prompts: De-Identification Traces Enhance Memorization Risks in Synthetic Chest X-Ray Generation | Feb 11, 2025 | BenchmarkingDe-identification | CodeCode Available | 0 |
| MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations | Feb 10, 2025 | BenchmarkingIn-Context Learning | —Unverified | 0 |
| Mitigating Sensitive Information Leakage in LLMs4Code through Machine Unlearning | Feb 9, 2025 | Code GenerationMachine Unlearning | —Unverified | 0 |
| A Lightweight Method to Disrupt Memorized Sequences in LLM | Feb 7, 2025 | Memorization | —Unverified | 0 |
| Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization | Feb 5, 2025 | DenoisingMemorization | —Unverified | 0 |
| An Analysis for Reasoning Bias of Language Models with Small Initialization | Feb 5, 2025 | Memorization | —Unverified | 0 |
| TReMu: Towards Neuro-Symbolic Temporal Reasoning for LLM-Agents with Memory in Multi-Session Dialogues | Feb 3, 2025 | MemorizationTimeline Summarization | —Unverified | 0 |
| Compositional Generalization Requires More Than Disentangled Representations | Jan 30, 2025 | Memorization | —Unverified | 0 |
| Integrating LMM Planners and 3D Skill Policies for Generalizable Manipulation | Jan 30, 2025 | MemorizationScene Understanding | —Unverified | 0 |
