{"ID":2838290,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18082","arxiv_id":"2511.18082","title":"ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models","abstract":"Recent Vision-Language-Action (VLA) models have shown impressive flexibility and generalization, yet their deployment in robotic manipulation remains limited by heavy computational overhead and inference latency. In this work, we present ActDistill, a general action-guided self-derived distillation framework that transfers the action prediction capability of any existing VLA model to a lightweight counterpart. Unlike previous efficiency strategies that primarily emphasize vision-language correlations, ActDistill leverages action priors to guide knowledge transfer and model compression, achieving action-oriented efficiency for VLA models. Specifically, we employ a well-trained VLA model as the teacher and introduce a graph-structured encapsulation strategy to explicitly model the hierarchical evolution of action prediction. The student model, derived from the graph-encapsulated teacher, is further equipped with a dynamic router that adaptively selects computation paths based on action prediction demands, guided by hierarchical graph-informed supervision to ensure smooth and efficient evolution. During inference, graph-related auxiliary components are removed, allowing the student to execute only dynamically routed layers and predict high-precision actions with minimal computation and latency. Experiments on embodied benchmarks demonstrate that ActDistill achieves comparable or superior performance to full-scale VLA models while reducing computation by over 50% with up to 1.67 times speedup, thereby establishing a general paradigm toward efficient embodied intelligence.","short_abstract":"Recent Vision-Language-Action (VLA) models have shown impressive flexibility and generalization, yet their deployment in robotic manipulation remains limited by heavy computational overhead and inference latency. In this work, we present ActDistill, a general action-guided self-derived distillation framework that trans...","url_abs":"https://arxiv.org/abs/2511.18082","url_pdf":"https://arxiv.org/pdf/2511.18082v3","authors":"[\"Wencheng Ye\",\"Tianshi Wang\",\"Lei Zhu\",\"Fengling Li\",\"Guoli Yang\",\"Hengtao Shen\"]","published":"2025-11-22T14:44:03Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.RO\"]","methods":"[]","has_code":false}