Skip to content

Author

Wei-Tong Zhang

6 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 Nov 2026

On the Feature Evolution of Temporal Difference Learning

Temporal-difference (TD) learning trains neural representations using bootstrapped targets generated by evolving value estimates, yet how predictive features emerge and propagate under incomplete neural updates remains poorly understood. We investigate this problem using finite-width two-layer ReLU critics on a constru...

Shang-Zhe Li, De-Chen Zhang, Di-Fan Zou et al. · 0 citations

REVO: Rollout-Efficient Off-Policy Distillation via Variance-Guided Reuse

On-policy distillation (OPD) trains language models using dense token-level teacher supervision on student-generated trajectories. However, its reliance on frequently refreshed student rollouts often incurs substantial generation cost. We introduce REVO, an off-policy distillation framework that improves rollout effici...

Yu-Xiao Yang, Shang-Zhe Li, Tian-Run Yu et al. · 0 citations
#machine learning Preprint Sep 2026

Provable Benefits of Regularization: Fast Rates for Adversarial Imitation Learning

Dually Regularized AIL is the first algorithm to simultaneously achieve $\widetilde{O}\left(\frac{1}{\epsilon}\right)$ sample complexity in both expert demonstrations and online interactions for this regularized AIL objective, even with stochastic experts.

Hang Zhou, Shang-Zhe Li, А. А. Браверман et al. · 0 citations

Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It

CIS replaces the unbounded second moment that governs the error of exact importance sampling with a term bounded by a constant, at the cost of a bias controlled by the truncated excess, in evaluation across three mixture-of-experts models and five mathematical reasoning benchmarks.

Tian-Run Yu, Kai-Xiang Zhao, Shang-Zhe Li et al. · 1 citation
#machine learning Preprint Sep 2026

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

We study length inflation in on-policy distillation (OPD), where student responses can become excessively long and even exhaust the generation budget. We identify \emph{termination-token mismatch} between base students and post-trained teachers as an important source of this behavior. Across Qwen3, Llama, and Gemma, th...

Yu-Xiao Yang, Tian-Run Yu, Shang-Zhe Li et al. · 4 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.