Shan You, Angelica Aviles-Rivero, Xiu Su, Hkust, Xi Lin, Qiang Chen, Yi Chen, Hongyan Xu, Chun-Wun Cheng
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Machine unlearning has become a crucial role in enabling generative models trained on large datasets to remove sensitive, private, or copyrightprotected data. However, existing machine unlearning methods face three challenges in learning to forget identity of generative models: 1) inefficient, where identity erasure requires finetuning all the model's parameters; 2) limited controllability, where forgetting intensity cannot be controlled and explainability is lacking; 3) catastrophic collapse, where the model's retention capability undergoes drastic degradation as forgetting progresses. Forgetting has typically been handled through discrete and unstable updates, often requiring full-model fine-tuning and leading to catastrophic collapse. In this work, we argue that identity forgetting should be modeled as a continuous trajectory, and introduce LEGATO -Learn to ForgEt Identity in GenerAtive Models via Trajectory-consistent Neural Ordinary Differential Equations. LEGATO augments pre-trained generators with fine-tunable lightweight Neural ODE adapters, enabling smooth, controllable forgetting while keeping the original model weights frozen. This formulation allows forgetting intensity to be precisely modulated via ODE step size, offering interpretability and robustness. To further ensure stability, we introduce trajectory consistency constraints that explicitly prevent catastrophic collapse during unlearning. Extensive experiments across in-domain and out-of-domain identity unlearning benchmarks show that LEGATO achieves stateof-the-art forgetting performance, avoids catastrophic collapse and reduces fine-tuned parameters. Codes are available at https://github.com/shqiangchen/LEGATO.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2601.04282")
get_code_for_paper("2601.04282")
have("2601.04282")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2601.04282.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2601.04282)
Connect an agent — have() is free.