Qingnan Ren

2 accepted papers

2026

Controlled LLM Training on Spectral Sphere

Tian Xie, Haoming Luo, Haoyu Tang, Hu Yiwen, Jason Liu, Qingnan Ren +6

ICML 2026oral

Scaling large models requires optimization strategies that ensure rapid convergence grounded in stability. Maximal Update Parametrization ($\boldsymbol{\mu}$P) provides a theoretical safeguard for width-invariant $\Theta(1)$ activation control, whereas emerging optimizers like Muon are only "half-al…

Cited by 0 Source ↗Scholar ↗

2026

Unbiased Principles, Robust Rewards

Qingnan Ren, Jinhao Jiang, Shiting Huang, Hanbin Wang, Lin Chen, Zehui Chen +1

ICML 2026poster

Reward models are central to Reinforcement Learning from Human Feedback (RLHF), especially for open-ended tasks where evaluation is inherently multi-dimensional. Recent Generative Reward Models (GRMs) improve interpretability by producing natural-language rationales and task-specific evaluation prin…

Cited by 0 Source ↗Scholar ↗