Jiayuan Ye
2 papers · Latest:
Artificial Intelligence
Generalization in LLM Problem Solving: The Case of the Shortest Path
LLMs generalize spatially but fail at length scaling in shortest-path problems due to recursive instability, despite various training improvements.
2604.15306
Natural Language ProcessingCram Less to Fit More: Training Data Pruning Improves Memorization of Facts
Training data pruning improves LLM factual memorization, enabling smaller models to match larger ones by optimizing information density.
2604.08519
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.