ASRU combines activation redirection and reward-optimized fine-tuning to unlearn cross-modal sensitive knowledge in MLLMs, reporting +24.6% better unlearning effectiveness and 5.8x higher generation quality on Qwen3-VL while preserving utility with limited retained data.
Rule: Reinforcement unlearning achieves forget-retain pareto optimality.arXiv preprint arXiv:2506.07171
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A penalty-based bi-level optimization framework for machine unlearning that decorrelates forget and retention gradients via inner maximization and restores utility via outer minimization, with convergence guarantees and improved trade-offs on vision and language benchmarks.
citing papers explorer
-
ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
ASRU combines activation redirection and reward-optimized fine-tuning to unlearn cross-modal sensitive knowledge in MLLMs, reporting +24.6% better unlearning effectiveness and 5.8x higher generation quality on Qwen3-VL while preserving utility with limited retained data.
-
OFMU: Optimization-Driven Framework for Machine Unlearning
A penalty-based bi-level optimization framework for machine unlearning that decorrelates forget and retention gradients via inner maximization and restores utility via outer minimization, with convergence guarantees and improved trade-offs on vision and language benchmarks.