Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Shizhe Diao

Shizhe Diao

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×1ML×1NLP×1

Frequent co-authors

Saurav Muralidharan2×
Pavlo Molchanov2×
Peter Belcak1×
Greg Heinrich1×
Ruida Wang1×
Rui Pan1×

Research Timeline

2026
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

This paper introduces Zone of Proximal Policy Optimization (ZPPO) for knowledge distillation, which keeps the teacher inside the student's current zone of development and outperforms off/on-policy distillation and GRPO.

Diffusion-Proof: Recipe for Formal Theorem Proving Beyond Auto-Regressive Generation

The paper proposes a framework called Diffusion-Proof to enhance the formal math reasoning capabilities of Large Language Models (LLMs) using diffusion LLMs.

CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse

The paper introduces agentic reasoning caching, a method to efficiently apply solutions to new problems using language models.

Highlighted terms show continued research focus across papers

Papers

cs.AIEmpiricalRecentNov 6, 2026

CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse

Peter Belcak, Greg Heinrich, Saurav Muralidharan, Shizhe Diao +1 more

The paper introduces agentic reasoning caching, a method to efficiently apply solutions to new problems using language models.

View →
cs.LGEmpiricalRecent
Jun 17, 2026

Diffusion-Proof: Recipe for Formal Theorem Proving Beyond Auto-Regressive Generation

Ruida Wang, Rui Pan, Pengcheng Wang, Shizhe Diao +1 more

The paper proposes a framework called Diffusion-Proof to enhance the formal math reasoning capabilities of Large Language Models (LLMs) using diffusion LLMs.

View →
cs.CLEmpiricalRecentJun 16, 2026

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

Byung-Kwan Lee, Ximing Lu, Shizhe Diao, Minki Kang +7 more

This paper introduces Zone of Proximal Policy Optimization (ZPPO) for knowledge distillation, which keeps the teacher inside the student's current zone of development and outperforms off/on-policy dis…

View →