Xuan Qi

Learning from real-world environments follows a precise log-sigmoid scaling law, with agent performance and learning speed improving dramatically over time.

Batch normalization's power comes from reshaping the geometry of neural network decision boundaries on a per-batch basis, not just from optimization benefits.

Chain-of-thought reasoning can actually *hurt* language agent performance in function-calling tasks, with brief reasoning outperforming both direct answers and lengthy deliberation.

LLMs align even better with human preferences when trained on *less* data, revealing that preference signals are surprisingly concentrated in the initial tokens of responses.