少走少读：通过免调优的多模态令牌剪枝提升视觉-语言导航效率
Walk and Read Less: Improving the Efficiency of Vision-and-Language Navigation via Tuning-Free Multimodal Token Pruning
AI总结：
本文提出导航感知剪枝NAP，通过前景/背景令牌预过滤、LLM提取导航相关指令及移除低重要性节点来抑制回溯，在保持更高VLN成功率的同时节省超过50%的FLOPS。
摘要：
大型模型在视觉-语言导航（VLN）任务上取得了很强的性能，但在资源受限环境中运行成本高昂。令牌剪枝通过减小模型输入规模，在效率与最小性能损失之间提供了有吸引力的权衡，但先前的工作忽视了VLN特有的挑战。例如，剪枝造成的信息损失实际上可能因为更长的行走路径而增加计算成本。因此，无法识别无信息令牌会削弱剪枝本应带来的效率提升。为了解决这一问题，我们提出了导航感知剪枝（Navigation-Aware Pruning，NAP），该方法利用导航特有的特征，通过将令牌预过滤为前景和背景来简化剪枝过程。例如，图像视图根据智能体能否朝该方向导航进行过滤。我们还使用大型语言模型提取与导航相关的指令。过滤之后，我们将剪枝重点放在背景令牌上，从而最小化信息损失。为了进一步帮助避免导航长度增加，我们通过移除低重要性导航节点来抑制回溯行为。在标准VLN基准上的实验表明，NAP显著优于先前的工作，在保持更高成功率的同时节省了超过50%的FLOPS。
英文摘要：
Large models achieve strong performance on Vision-and-Language Navigation (VLN) tasks, but are costly to run in resource-limited environments. Token pruning offers appealing tradeoffs for efficiency with minimal performance loss by reducing model input size, but prior work overlooks VLN-specific challenges. For example, information loss from pruning can effectively increase computational cost due to longer walks. Thus, the inability to identify uninformative tokens undermines the supposed efficiency gains from pruning. To address this, we propose Navigation-Aware Pruning (NAP), which uses navigation-specific traits to simplify the pruning process by pre-filtering tokens into foreground and background. For example, image views are filtered based on whether the agent can navigate in that direction. We also extract navigation-relevant instructions using a Large Language Model. After filtering, we focus pruning on background tokens, minimizing information loss. To further help avoid increases in navigation length, we discourage backtracking by removing low-importance navigation nodes. Experiments on standard VLN benchmarks show NAP significantly outperforms prior work, preserving higher success rates while saving more than 50% FLOPS.
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。
