ICML 2025 Workshop MUGen Submissions

Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearning
Prabhav Sanga, Jaskaran Singh, ARUN KUMAR DUBEY
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
WaterDrum: Watermarking for Data-centric Unlearning Metric
Xinyang Lu, Xinyuan Niu, Gregory Kang Ruey Lau, Bui Thi Cam Nhung, Rachael Hwee Ling Sim, Fanyu Wen, Chuan-Sheng Foo, See-Kiong Ng, Bryan Kian Hsiang Low
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Data-Unlearn-Bench: Making Evaluating Data Unlearning Easy
Roy Rinberg, Pol Puigdemont, Martin Pawelczyk, Volkan Cevher
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
ContinualFlow: Learning and Unlearning with Neural Flow Matching
Lorenzo Simone, Davide Bacciu, Shuangge Ma
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Ascent Fails to Forget
Ioannis Mavrothalassitis, Pol Puigdemont, Noam Itzhak Levi, Volkan Cevher
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
An Empirical Exploration of Continual Unlearning for Image Generation
Justin Lee, Zheda Mai, Chongyu Fan, Wei-Lun Chao
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Koopman Autoencoders Learn Neural Representation Dynamics
Nishant Suresh Aswani, Saif Jabari
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Understanding Machine Unlearning Through the Lens of Mode Connectivity
Jiali Cheng, Hadi Amiri
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Noisy But Forgotten: LLM Unlearning are Robust against Perturbed Data in the Wild
Changsheng Wang, Yihua Zhang, Jinghan Jia, Dennis Wei, Sijia Liu
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
Yiwei Chen, Soumyadeep Pal, Yimeng Zhang, Qing Qu, Sijia Liu
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Oral
- Readers: Everyone
Unveiling Concept Attribution in Diffusion Models
Quang H Nguyen, Hoang Phan, Khoa D Doan
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Reveal-or-Obscure: A Differentially Private Sampling Algorithm
Naima Tasnim, Atefeh Gilani, Lalitha Sankar, Oliver Kosut
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Rethinking Unlearning for Large Reasoning Models
Changsheng Wang, Chongyu Fan, Yihua Zhang, Jinghan Jia, Dennis Wei, Parikshit Ram, Nathalie Baracaldo, Sijia Liu
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Machine Unlearning under Overparameterization
Jacob L. Block, Aryan Mokhtari, Sanjay Shakkottai
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Gauss-Newton Unlearning for the LLM Era
Lev E McKinney, Anvith Thudi, Juhan Bae, Tara Rezaei Kheirkhah, Nicolas Papernot, Sheila A. McIlraith, Roger Baker Grosse
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Rethinking Backdoor Unlearning Through Linear Task Decomposition
Amel Abdelraheem, Alessandro Favero, Gérôme Bovet, Pascal Frossard
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Embarrassingly Efficient Unlearning with SVD
Marcin Sendera, Łukasz Struski, Kamil Książek, Kryspin Musiol, Jacek Tabor, Dawid Damian Rymarczyk
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Tracing and Reversing Rank-One Model Edits
Paul Youssef, Zhixue Zhao, Christin Seifert, Jörg Schlötterer
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
On the Fragility of Latent Knowledge: Layer-wise Influence under Unlearning in Large Language Model
Jianing Zhu, Zongze Li, Chandler Squires, Qizhou Wang, Bo Han, Pradeep Ravikumar
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models
Ziheng Cheng, Yixiao Huang, Hui Xu, Somayeh Sojoudi, Xuandong Zhao, Dawn Song, Song Mei
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge
Scott Mahan, Eric Yeats, Darryl Hannan, Henry Kvinge, Timothy Doster
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Unleashing Uncertainty: Efficient Machine Unleanring for Generative AI
Christoforos N. Spartalis, Theodoros Semertzidis, Petros Daras, Stratis Gavves
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Evaluating Deep Unlearning in Large Language Models
Ruihan Wu, Chhavi Yadav, Ruslan Salakhutdinov, Kamalika Chaudhuri
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
Yaxuan Wang, Quan Liu, Chris Yuhao Liu, Jinlong Pang, Wei Wei, Yujia Bao, Yang Liu
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone
Model Unlearning via Sparse Autoencoder Subspace Guided Projections
Xu Wang, Zihao Li, Benyou Wang, Yan Hu, Difan Zou
- Published: 11 Jun 2025, Last Modified: 11 Jun 2025
- MUGen @ ICML 2025 Poster
- Readers: Everyone