See Less, Specify More: Visual Evidence Budgets for Generalizable VLAs 文章

ArXiv CS.AI2026-06-03NEWSen作者: Yueh-Hua Wu, Tatsuya Matsushima, Kei Ota

摘要

arXiv:2606.02735v1 Announce Type: cross Abstract: Generalization remains a central bottleneck for vision-language-action (VLA) models: under distractors, appearance shifts, and semantically similar tasks, the policy must often infer local execution details from coarse instructions while also deciding which parts of the image matter for control. We present S2 (See Less, Specify More), a framework for improving VLA generalization by training the executor under a cleaner interface. Specify More preserves the original instruction as a stable high-level goal while relabeling each trajectory into refined trajectory- and subtask-level language that disambiguates the current execution mode. Unlike native attention, See Less imposes an explicit visual evidence budget, training the executor to act from task-sufficient evidence rather than unconstrained visual context, without any region or mask annotation.

相关公司

暂无数据

相关人物

暂无数据

相关产品查看全部 (1)