Zijian Zeng

[6] viXra:2605.0120 submitted on 2026-05-31 18:47:17 , (0 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

[5] viXra:2605.0119 submitted on 2026-05-31 03:02:06 , (0 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

[4] viXra:2605.0118 submitted on 2026-05-31 03:04:00 , (0 unique-IP downloads)

Check Token: Real-Time Self-Verification and Precise Truncation in LLM Reasoning

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

[3] viXra:2605.0117 submitted on 2026-05-31 03:05:42 , (0 unique-IP downloads)

On the Impossibility of Unbiased and Length-Invariant Policy Optimization with Outcome Rewards

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

[2] viXra:2604.0059 replaced on 2026-04-26 07:19:04 , (123 unique-IP downloads)

Reducing Credit Assignment Variance via Counterfactual Reasoning Paths

Authors: Fei Ding, Yongkang Zhang, Yeling Peng, Youwei Wang, Guoxiong Zhou, Zijian Zeng
Category: Artificial Intelligence

[1] viXra:2604.0058 submitted on 2026-04-15 20:10:37 , (60 unique-IP downloads)

Design Conditions for Intra-Group Learning of Sequence-Level Rewards: Token Gradient Cancellation

Authors: Fei Ding, Yongkang Zhang, Youwei Wang, Zijian Zeng
Category: Artificial Intelligence