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

Zhengyu Qi

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

NLP×1AI×1Distributed×1Networking×1Performance×1

Frequent co-authors

Sijie Wang1×
Zhengyu Qing1×
Zhiqiang Tan1×
Yiming Yin1×
Yeqing Zhang1×
Yaoyuan Wang1×

Research Timeline

2026
Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation

DigenRL is a disaggregated RL framework for diffusion-based generative LLMs that achieves 1.56-2.10x throughput improvements over state-of-the-art diffusion RL systems.

Dynamic Commonsense Coordination for Empathetic Response Generation

This paper proposes DCC, a Dynamic Commonsense Coordination Framework for Empathetic Response Generation, consisting of three modules: SCE-AttnRes, AGCF, and ICAD.

Highlighted terms show continued research focus across papers

Papers

cs.CLEmpiricalRecentJul 24, 2026

Dynamic Commonsense Coordination for Empathetic Response Generation

Zhengyu Qi

This paper proposes DCC, a Dynamic Commonsense Coordination Framework for Empathetic Response Generation, consisting of three modules: SCE-AttnRes, AGCF, and ICAD.

View →
cs.AIcs.DCcs.NIEmpirical
Recent
Jun 23, 2026

Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation

Sijie Wang, Zhengyu Qing, Zhiqiang Tan, Yiming Yin +5 more

DigenRL is a disaggregated RL framework for diffusion-based generative LLMs that achieves 1.56-2.10x throughput improvements over state-of-the-art diffusion RL systems.

View →