让模型推理时排除无关动作，更准规划操作步骤
Contrastive Energy Fields for Inference-Time Procedure Planning in Instructional Videos
- 构建动作条件表征空间，推理时动态筛选合理动作
- 在两个基准数据集上达到当前最佳准确率
- 适合需要逻辑约束的流程规划任务
流程规划旨在从初始状态推断出到达目标状态所需的动作序列。现有方法通过前馈神经网络或基于扩散的推理直接从潜在表示预测动作序列，但将所有动作视为可能，无法强制执行任务特定的逻辑约束，导致某些动作虽可生成却不合理。本文提出CEFITO，一种学习动作条件表征空间的规划方法。在此表征基础上，将流程规划建模为任务约束优化问题。与以往方法不同，CEFITO在推理阶段显式排除不相关的动作，实现更有效的流程规划，在两个主流流程规划基准测试中均取得当前最优性能。
原文摘要 · Abstract (English)
Procedure planning seeks to estimate a sequence of actions to transition from an observed initial state to a given goal state. Current procedure planning approaches directly predict action sequences from latent representations using feed-forward neural networks or diffusion-based inference. These paradigms treat every action as plausible, lacking the ability to enforce task-specific logical constraints that render certain actions irrelevant or not plausible. We propose CEFITO, a procedure planning approach that learns a predictor to express an action-conditioned representation space. Based on this representation space, we formulate procedure planning as a task-constrained optimization problem. Unlike prior methods, CEFITO explicitly reasons over the action space by omitting irrelevant actions during inference-time planning. This reformulation enables effective procedure planning and achieves state-of-the-art accuracy on two established procedure planning benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。