ICML 2025PastLarge language modelsSafety & alignment
The Impact of Memorization on Trustworthy Foundation Models: ICML 2025 Workshop
MemFM
- Submission deadline
- May 28, 2025, 11:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (25)
Fetched from OpenReview (v2) on 2026-06-10.
A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
An Empirical Exploration of Continual Unlearning for Image Generation
Are Samples Extracted From Large Language Models Memorized?
Bigger Isn’t Always Memorizing: Early Stopping Overparameterized Diffusion Models
ContextLeak: Auditing Leakage in Private In-Context Learning Methods
Counterfactual Influence as a Distributional Quantity
Early-stopping Too Late? Traces of Memorization Before Overfitting in Generative Diffusion
Evaluating Memorization in Parameter-Efficient Fine-tuning
GenAI Copyright Evidence with Operational Meaning
How Can I Publish My LLM Benchmark Without Giving the True Answers Away?
Knowledge‑Distilled Memory Editing for Plug‑and‑Play LLM Alignment
Language models’ activations linearly encode training-order recency
Localizing and Mitigating Memorization in Image Autoregressive Models
Low Resource Reconstruction Attacks Through Benign Prompts
Low-Rank Adaptation Secretly Imitates Differentially Private SGD
MAGIC: Diffusion Model Memorization Auditing via Generative Image Compression
Mirage of Mastery: Memorization Tricks LLMs into Artificially Inflated Self-Knowledge
Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs
OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
Personal Information Parroting in Language Models
Rethinking Memorization Measures in LLMs: Recollection vs. Counterfactual vs. Contextual Memorization
Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs
Trade-offs in Data Memorization via Strong Data Processing Inequalities