Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity

Documenti analoghi

• What does the Knowledge Neuron Thesis Have to do with Knowledge?
  di: Niu, Jingcheng, et al.
  Pubblicazione: (2024)
• All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs
  di: Chen, Xi, et al.
  Pubblicazione: (2026)
• What Would You Ask When You First Saw $a^2+b^2=c^2$? Evaluating LLM on Curiosity-Driven Questioning
  di: Javaji, Shashidhar Reddy, et al.
  Pubblicazione: (2024)
• Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs
  di: Fu, Yao, et al.
  Pubblicazione: (2025)
• Pruning Minimal Reasoning Graphs for Efficient Retrieval-Augmented Generation
  di: Wang, Ning, et al.
  Pubblicazione: (2026)