Abstract
Vision-Language-Action (VLA) models demonstrate impressive zero-shot generalization but frequently suffer from a "Precision-Reasoning Gap" in cluttered environments. This failure is driven by background-induced feature dilution, where high-frequency semantic noise corrupts the geometric grounding required for precise manipulation. To bridge this gap, we propose Concept-Gated Visual Distillation (CGVD), a training-free, model-agnostic inference framework that stabilizes VLA policies. CGVD operates by parsing instructions into safe and distractor sets, utilizing a two-layer target refinement process--combining cross-validation and spatial disambiguation--to explicitly penalize false positives and isolate genuine manipulation targets. We then process the scene via Fourier-based inpainting, generating a clean observation that actively suppresses semantic distractors while preserving critical spatial geometry and visual proprioception. Extensive evaluations in highly cluttered manipulation tasks demonstrate that CGVD prevents performance collapse. In environments with dense semantic distractors, our method significantly outperforms state-of-the-art baselines, achieving a 77.5% success rate compared to the baseline's 43.0%. By enforcing strict attribute adherence, CGVD establishes inference-time visual distillation as a critical prerequisite for robust robotic manipulation in the clutter.
Abstract (translated)
视觉-语言-行动（VLA）模型在零样本泛化方面表现出色，但在杂乱环境中往往会出现“精度推理差距”。这种失败主要是由于背景诱导的特征稀释所导致，其中高频语义噪声会破坏精确操作所需的几何基础。为了弥合这一差距，我们提出了概念门控视觉蒸馏（Concept-Gated Visual Distillation, CGVD），这是一种无需训练、模型无关的推理框架，用于稳定VLA策略。 CGVD通过将指令解析为安全集和干扰集，并利用两层目标细化过程——结合交叉验证与空间消歧——来明确惩罚假阳性并隔离真实的操作目标。然后，我们采用基于傅里叶的方法进行场景处理，在抑制语义干扰的同时保持关键的空间几何结构和视觉自我感知。在高度杂乱的操作任务中的广泛评估表明，CGVD可以防止性能崩溃。 在密集的语义干扰环境中，我们的方法显著优于最先进的基线模型，成功率达到了77.5%，而基线的成功率仅为43.0%。通过强制执行严格的属性遵守，CGVD建立了推理时间视觉蒸馏作为机器人杂乱环境操作稳健性的关键前提条件。
URL
https://arxiv.org/abs/2603.10340
