VLA-Forget：面向具身基础模型的视觉-语言-动作去学习
VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models
AI总结：
本文提出VLA-Forget框架，通过结合感知选择性编辑与层选择性推理去学习，提升去学习效果，保留感知特性和推理能力，减少量化恢复。
摘要：
视觉-语言-动作（VLA）模型正在成为机器人操作的具身基础模型，但其部署引入了新的去学习挑战：在不降级感知、语言定位和动作控制的情况下，去除不安全、虚假或隐私敏感的行为。在OpenVLA风格策略中，行为通过融合的视觉编码器、跨模态投影器和语言骨干预测分词机器人动作生成，因此不希望的知识可以分布在感知、对齐和推理/动作层，而不是局限于单一模块。因此，仅对视觉堆栈或仅对语言骨干进行部分去学习通常不足，而传统为独立视觉或语言模型设计的去学习基线在具身设置中可能留下残余遗忘或造成不必要的效用损失。我们提出了VLA-Forget，一种混合去学习框架，结合比率感知选择性编辑用于感知和跨模态特异性与层选择性推理/动作去学习用于效用保留遗忘。VLA-Forget通过分阶段更新视觉编码器、投影器和上层动作生成Transformer块，联合优化三个目标：目标遗忘、感知保留和推理保留。在forget-set行为探测和retain-task评估中，VLA-Forget相比强去学习基线提升了10%的遗忘效果，保留了22%的感知特性和9%的推理和任务成功率，并将量化后恢复减少了55%。
英文摘要：
Vision-language-action (VLA) models are emerging as embodied foundation models for robotic manipulation, but their deployment introduces a new unlearning challenge: removing unsafe, spurious, or privacy-sensitive behaviors without degrading perception, language grounding, and action control. In OpenVLA-style policies, behavior is produced through a fused visual encoder, a cross-modal projector, and a language backbone that predicts tokenized robot actions, so undesirable knowledge can be distributed across perception, alignment, and reasoning/action layers rather than confined to a single module. Consequently, partial unlearning applied only to the vision stack or only to the language backbone is often insufficient, while conventional unlearning baselines designed for standalone vision or language models may leave residual forgetting or incur unnecessary utility loss in embodied settings. We propose VLA-Forget, a hybrid unlearning framework that combines ratio-aware selective editing for perception and cross-modal specificity with layer-selective reasoning/action unlearning for utility-preserving forgetting. VLA-Forget jointly optimizes three objectives: targeted forgetting, perceptual preservation, and reasoning retention, through staged updates over the visual encoder, projector, and upper action-generating transformer blocks. Across forget-set behavior probes and retain-task evaluations, VLA-Forget improves forgetting efficacy by 10%, preserves perceptual specificity by 22%, retains reasoning and task success by 9%, and reduces post-quantization recovery by 55% relative to strong unlearning baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
