Runhao Liu

[3] viXra:2608.0055 submitted on 2026-08-14 20:41:21 , (50 unique-IP downloads)

Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery

Authors: Fei Ding, Runhao Liu, Yongkang Zhang, Yuhao Liao, Zijian Zeng, Huiming Yang
Category: Artificial Intelligence

[2] viXra:2605.0120 submitted on 2026-05-31 18:47:17 , (88 unique-IP downloads)

State Commitment Learning: Training Language Models to Distinguish Computation from Memory

Authors: Fei Ding, Yongkang Zhang, Runhao Liu, Yuhao Liao, Zijian Zeng, Huiming Yang
Category: Artificial Intelligence

[1] viXra:2605.0119 submitted on 2026-05-31 03:02:06 , (150 unique-IP downloads)

Scaffold-Mediated Post-Training: Co-Evolving Model Parameters and Procedural Scaffold Graphs

Authors: Fei Ding, Yongkang Zhang, Runhao Liu, Yuhao Liao, Zijian Zeng, Huiming Yang
Category: Artificial Intelligence