類似資料

• A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation
  著者:: Tu, Yiwen, 等
  出版事項: (2024)
• A Unified Theory of Random Projection for Influence Functions
  著者:: Hu, Pingbang, 等
  出版事項: (2026)
• GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection
  著者:: Hu, Pingbang, 等
  出版事項: (2025)
• PostTrainBench: Can LLM Agents Automate LLM Post-Training?
  著者:: Rank, Ben, 等
  出版事項: (2026)
• Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective
  著者:: Gan, Zeyu, 等
  出版事項: (2024)