Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models

• 类型：arxiv
• 标识：2608.23478
• 链接：https://arxiv.org/abs/2608.23478
• 主分类：multimodal
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar + OpenAlex
• S2被引：0
• OpenAlex被引：0
• 影响力被引：0
• TLDR：Intention Distillation (INDI) is proposed, which distills behavior-level intent into the action decoder and organizes downstream predictions in an objective-dependent manner, and shows that action decoders benefit from explicitly modeling the semantic objective of the behavior they generate.
• OpenAlex ID：W7204155848
• OpenAlex DOI：10.48550/arxiv.2608.23478
• DOI：10.48550/arxiv.2608.23478
• DOI来源：OpenAlex
• 开放获取：green
• 开放获取链接：https://arxiv.org/pdf/2608.23478
• OpenAlex更新：2026-09-02
• 待LLM分类：否
• 标题中文：按意图行动：面向视觉-语言-动作模型的行为意图蒸馏
• TLDR中文：提出 Intention Distillation (INDI)，将行为级意图蒸馏到动作解码器中，并以目标依赖的方式组织下游预测；研究表明，动作解码器显式建模其生成行为的语义目标能够带来收益。
• 来源文件：
• /inbox/tom/_candidates/2026-08-31-agent-rag-longcontext-candidates.json
• /inbox/tom/_candidates/2026-09-01-rag-retrieval-reranking-candidates.json
• /inbox/tom/_candidates/2026-09-01-agent-rag-longcontext-candidates.json
• [OpenAlex backfill]
• [S2 enrich]