CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
Vision-language models (VLMs) have shown remarkable ability in aligning visual and textual representations, enabling a wide range of multimodal applications. However, their large-scale training data inevitably raises concerns about privacy, copyright, and undesirable content, creating a strong need for machine unlearning. While existing studies mainly focus on single-shot unlearning, practical VLM deployment often involves sequential removal requests over time, giving rise to continual machine u
Record details
Published: 18 May 2026
Source: arXiv
Category: Research
Topics: Privacy · Copyright & IP
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets
arXiv · 27 May 2026
Challenges to Grassroots Organization Engagement with AI Policy
arXiv · 18 June 2026
Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition
arXiv · 9 April 2026
AI and Doctrinal Collapse
Harvard Berkman Klein Center · 30 June 2026
TILDE: TILt-based Distributional Erasure for Concept Unlearning
arXiv · 7 July 2026
GlucoTune: A Unified Framework for Blood Glucose Preprocessing, Forecasting, and Benchmarking in Diabetes
arXiv · 23 July 2026
How to cite this record
ethics.ai (18 May 2026), “CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic,” evidence record 4103, https://ethics.ai/record/4103 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.