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

Qi Wang

7 indexed papers

Recent (6 mo)
7
With code
0
Influential cites
0
Benchmarked
0

Publications per year

7
26

Top categories

AI×6ML×5Vision×1Crypto×1NLP×1

Frequent co-authors

Heming Zou3×
Yun Qu3×
Yixiu Mao3×
Xiangyang Ji3×
Ning Lu2×
Baijiong Lin2×

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.

Policy and World Modeling Co-Training for Language Agents

The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent performance.

Policy and World Modeling Co-Training for Language Agents

The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent performance.

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.

Automated jailbreak attack targeting multiple defense strategies

The paper presents UNIATTACK, a framework for constructing effective black-box attack prompts for large language models.

Texture++: Elevating 3D Asset Texture Resolution with a Region-Aware Diffusion Model

The paper introduces Texture++, a framework for enhancing low-resolution textures in 3D assets using a diffusion-based super-resolution model and adaptive view selection strategy.

Highlighted terms show continued research focus across papers

Papers

cs.CVEmpiricalRecentJul 23, 2026

Texture++: Elevating 3D Asset Texture Resolution with a Region-Aware Diffusion Model

Shuaiwei Wang, Shi Li, Jieting Xu, Yuchi Huo +3 more

The paper introduces Texture++, a framework for enhancing low-resolution textures in 3D assets using a diffusion-based super-resolution model and adaptive view selection strategy.

View →
cs.CRcs.AIEmpirical
Recent
Jun 15, 2026

Automated jailbreak attack targeting multiple defense strategies

Qi Wang, Chengcheng Wan, Weijia He, Yanqing Li +3 more

The paper presents UNIATTACK, a framework for constructing effective black-box attack prompts for large language models.

View →
cs.LGcs.AIcs.CLEmpiricalRecentJun 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.AIRecentJun 1, 2026

Policy and World Modeling Co-Training for Language Agents

Ning Lu, Baijiong Lin, Shengcai Liu, Jiahao Wu +8 more

The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent perf…

View →
cs.LGcs.AIRecentJun 1, 2026

Policy and World Modeling Co-Training for Language Agents

Ning Lu, Baijiong Lin, Shengcai Liu, Jiahao Wu +8 more

The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent perf…

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 →