Chenruo Liu

2 accepted papers

2026

A Task-centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula

Chenruo Liu, Yijun Dong, Yiqiu Shen, Qi Lei

ICML 2026poster

Iterative self-improvement fine-tunes an autoregressive large language model (LLM) on reward-verified outputs generated by the LLM itself. In contrast to the empirical success of self-improvement, the theoretical foundation of this generative, iterative procedure in a practical, finite-sample settin…

Cited by 0 Source ↗Scholar ↗

2026

Does Weak-to-strong Generalization Happen under Spurious Correlations?

Chenruo Liu, Yijun Dong, Qi Lei

ICLR 2026poster

We initiate a unified theoretical and algorithmic study of a key problem in weak-to-strong (W2S) generalization: when fine-tuning a strong pre-trained student with pseudolabels from a weaker teacher on a downstream task with spurious correlations, does W2S happen, and how to improve it upon failures…

Cited by 0 Source ↗Scholar ↗