類似資料

• The Geometries of Truth Are Orthogonal Across Tasks
  著者:: Azizian, Waiss, 等
  出版事項: (2025)
• Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
  著者:: Bethune, Louis, 等
  出版事項: (2025)
• Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training
  著者:: Krajewski, Jakub, 等
  出版事項: (2025)
• The Data-Quality Illusion: Rethinking Classifier-Based Quality Filtering for LLM Pretraining
  著者:: Saada, Thiziri Nait, 等
  出版事項: (2025)
• Distillation Scaling Laws
  著者:: Busbridge, Dan, 等
  出版事項: (2025)