ICML 2025 Past Generative models
ICML 2025 Workshop on Machine Unlearning for Generative AI
MUGen @ ICML 2025
- Submission deadline
- May 24, 2025, 11:59 UTC imported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).
Accepted papers (36)
Fetched from OpenReview (v2) on 2026-06-10.
-
Align-then-Unlearn: Embedding Alignment for LLM Unlearning
-
An Empirical Exploration of Continual Unlearning for Image Generation
-
Ascent Fails to Forget
-
Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge
-
Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images
-
Breaking Weight Entanglement: Machine Unlearning with Nonlinearity
-
ContinualFlow: Learning and Unlearning with Neural Flow Matching
-
Data-Unlearn-Bench: Making Evaluating Data Unlearning Easy
-
Distributional Unlearning: Forgetting Distributions, Not Just Samples
-
Do Not Mimic My Voice: Speaker Identity Unlearning for Zero-Shot Text-to-Speech
-
DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
-
Embarrassingly Efficient Unlearning with SVD
-
Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
-
Evaluating Deep Unlearning in Large Language Models
-
Gauss-Newton Unlearning for the LLM Era
-
GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection
-
Koopman Autoencoders Learn Neural Representation Dynamics
-
Learning-Time Encoding Shapes Unlearning in LLMs
-
Machine Unlearning under Overparameterization
-
Model Unlearning via Sparse Autoencoder Subspace Guided Projections
-
Noisy But Forgotten: LLM Unlearning are Robust against Perturbed Data in the Wild
-
On the Fragility of Latent Knowledge: Layer-wise Influence under Unlearning in Large Language Model
-
OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models
-
Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check
-
Rethinking Backdoor Unlearning Through Linear Task Decomposition
-
Rethinking Evaluation Metrics for Machine Unlearning
-
Rethinking Unlearning for Large Reasoning Models
-
Reveal-or-Obscure: A Differentially Private Sampling Algorithm
-
Selective Knowledge Unlearning via Self-Distillation with Auxiliary Forget-Set Model
-
Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearning
-
Understanding Machine Unlearning Through the Lens of Mode Connectivity
-
Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
-
Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI
-
Unveiling Concept Attribution in Diffusion Models
-
WaterDrum: Watermarking for Data-centric Unlearning Metric
-
When to Forget? Complexity Trade-offs in Machine Unlearning