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

Xiangyang Ji

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

ML×3AI×3Software Eng.×1Formal Lang.×1NLP×1

Frequent co-authors

Heming Zou3×
Qi Wang3×
Yun Qu3×
Yixiu Mao3×
Ran Wei1×
Le Zhu1×

Research Timeline

2026
RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning

The paper introduces Group Prioritized Off-Policy Optimization (POPO), a novel framework that efficiently accelerates RL finetuning for LLM reasoning by leveraging effective off-policy training batches without requiring costly additional data rollouts.

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning

The paper introduces Group Prioritized Off-Policy Optimization (POPO), a novel framework that efficiently accelerates RL finetuning for LLM reasoning by leveraging effective off-policy training batches without requiring costly additional data rollouts.

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

This paper introduces a new rollout allocation framework for enhancing reward contrast in reinforcement learning with large language models.

Formal-Method-Guided Vibe Coding: Closing the Verification Loop on AI-Generated Safety-Critical Software Through Model-Driven Engineering

This paper presents Forge, a pipeline that uses formal verification to ensure the safety and certification of LLM-generated Java code.

Highlighted terms show continued research focus across papers

Papers

cs.SEcs.FLEmpiricalRecentJun 21, 2026

Formal-Method-Guided Vibe Coding: Closing the Verification Loop on AI-Generated Safety-Critical Software Through Model-Driven Engineering

Ran Wei, Le Zhu, Haochi Wang, Jim Woodcock +3 more

This paper presents Forge, a pipeline that uses formal verification to ensure the safety and certification of LLM-generated Java code.

View →
cs.LGcs.AIcs.CLEmpirical
Recent
Jun 9, 2026

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

Heming Zou, Qi Wang, Yun Qu, Yuhang Jiang +8 more

This paper introduces a new rollout allocation framework for enhancing reward contrast in reinforcement learning with large language models.

View →
cs.LGcs.AIRecentMay 31, 2026

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning

Yixiu Mao, Yun Qu, Qi Wang, Heming Zou +1 more

The paper introduces Group Prioritized Off-Policy Optimization (POPO), a novel framework that efficiently accelerates RL finetuning for LLM reasoning by leveraging effective off-policy training batche…

View →
cs.LGcs.AIRecentMay 31, 2026

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning

Yixiu Mao, Yun Qu, Qi Wang, Heming Zou +1 more

The paper introduces Group Prioritized Off-Policy Optimization (POPO), a novel framework that efficiently accelerates RL finetuning for LLM reasoning by leveraging effective off-policy training batche…

View →