Skip to content
Hot eventLive

CADT:扩散模型反事实轨迹归因方法

1 reports1 sources3 hr ago updated

Get the story

AI overview

2026年10月9日,arXiv(Computer Vision,一手来源)报道了一种扩散模型数据归因新方法 CADT(Concept Attribution through Dynamic Trajectories,基于动态轨迹的概念归因)。该方法把数据归因问题重构为对因子诱发的内部响应轨迹的归因,强调追踪训练数据如何影响模型内部动态(HOW),而非仅识别哪些数据被使用(WHICH)。目前公开信息仅包含该论文的核心思路,尚未见后续实验验证、代码发布或同行评议结果。

Generated from reports · updated 3 hr ago

Timeline

Follow the coverage from different angles.

Oct 9, 2026
  1. arXiv · Computer Vision
    扩散模型数据归因新方法 CADT:追踪 HOW 而非仅 WHICH

    论文提出扩散模型归因方法 CADT(Concept Attribution through Dynamic Trajectories),把数据归因重构为对因子诱发的内部响应轨迹的归因。

Heat trend

Current heat 9·Comparable peak 10(Oct 9)·Comparable change over 24 hours –

02.557.510Oct9Oct9Oct9Oct9

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.