Yihong Dong

Theoretical Proof that Auto-regressive Language Models Collapse when Real-world Data is a Finite Set

2024 · arXiv (Cornell University)

Auto-regressive language models (LMs) have been widely used to generate data in data-scarce domains to train new LMs, compensating for the scarcity of real-world data. Previous work experimentally found that LMs collapse when trained on …

Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute

2025 · arXiv (Cornell University)

Recent advancements in software engineering agents have demonstrated promising capabilities in automating program improvements. However, their reliance on closed-source or resource-intensive models introduces significant deployment challenges in private environments, prompting a critical question: \textit{How can …