類似資料

• The Role of Sparsity for Length Generalization in Transformers
  著者:: Golowich, Noah, 等
  出版事項: (2025)
• Repeat After Me: Transformers are Better than State Space Models at Copying
  著者:: Jelassi, Samy, 等
  出版事項: (2024)
• LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks
  著者:: Prabhakar, Akshara, 等
  出版事項: (2024)
• Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining
  著者:: Zhao, Rosie, 等
  出版事項: (2025)
• Loss-to-Loss Prediction: Scaling Laws for All Datasets
  著者:: Brandfonbrener, David, 等
  出版事項: (2024)