SheepNav
新上线今天0 投票

Transformer Geometry Observatory TGO-IV: Developmental Topology Observatory

arXiv:2608.09997v1 Announce Type: new Abstract: Transformers have had a profound impact on the world of language processing and computer vision. As efforts to answer the million-dollar question of ``How does a Transformer learn?" have been increasing, existing interpretability studies primarily analyze representations at isolated layers or the network as a whole, while the developmental evolution of individual representations and its manifolds across transformer layers remains underexplored. Wit

延伸阅读

  1. 从垃圾信息中寻找信号:联合学习奖励与工人可靠性的新方法
  2. UserToolBench:面向工具使用大模型的个性化决策新基准
  3. FlowScout:从执行反馈到可靠的工具使用代理工作流
查看原文