Author

Tong Che

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

Rare Gate Disagreements Can Limit Plasticity: When Gradient Flow Mispredicts Finite-Batch SGD

Population gradient flow is a common tool for reasoning about how neural networks adapt, including after pretraining. We show that it can mispredict finite-batch stochastic gradient descent (SGD) qualitatively, and we trace the discrepancy to a specific mechanism. In a two-unit ReLU regression, a source task drives the...

Ruo-Yu Zhao, Ming-Xuan Zhang, Jian-Bo Dai et al. · 0 citations

#artificial intelligence Jun 2026

Greed Is Learned: Visible Incentives as Reward-Hacking Triggers

In MoneyWorld, a synthetic workplace environment, five instruction-tuned models from three families with RL are trained on non-safety tasks in which a visible payoff signal identifies a rewarded shortcut that sacrifices task quality.

Tong Che, Rui Wu · arXiv.org · 0 citations