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

Han Zhao

6 indexed papers

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

Publications per year

6
26

Top categories

AI×3Sound×2Audio and Speech Processing×2ML×2Distributed×1Performance×1Crypto×1

Frequent co-authors

Xiangang Li2×
Haoxu Wang2×
Yifei He2×
Rui Yang2×
Hao Bai2×
Tong Zhang2×

Research Timeline

2026
PRO-CUA: Process-Reward Optimization for Computer Use Agents

PRO-CUA introduces a process-reward optimization framework that enables efficient, step-level reinforcement learning for training computer use agents by decoupling environment interaction from policy optimization.

PRO-CUA: Process-Reward Optimization for Computer Use Agents

PRO-CUA introduces a process-reward optimization framework that enables efficient, step-level reinforcement learning for training computer use agents by decoupling environment interaction from policy optimization.

RogueMerge: Robust and Unified Attacks against LLM Model Merging

RogueMerge introduces a unified framework to robustly attack LLM model merging by addressing the challenges of autoregressive decoding, unknown merging configurations, and prompt generalization, significantly outperforming prior methods.

GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving

GF-DiT: A policy-programmable runtime for elastic DiT serving

FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech

This paper presents FlowTTS-GRPO, an online RL framework for Flow-Matching based Text-to-Speech that enables direct fine-tuning of open-source models.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering

This paper introduces a unified framework for generating high-quality full-length music from lyrics, text descriptions, and musical attributes, consisting of a semantic-aware tokenizer, hybird-LM, FullDiT, and a two-level melody module.

Highlighted terms show continued research focus across papers

Papers

cs.SDcs.AIeess.ASEmpiricalRecentJul 22, 2026

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering

Junyu Dai, Xinyue Fan, Weiqin Li, Xiangang Li +12 more

This paper introduces a unified framework for generating high-quality full-length music from lyrics, text descriptions, and musical attributes, consisting of a semantic-aware tokenizer, hybird-LM, Ful…

View →
eess.AScs.SDEmpirical
Recent
Jun 22, 2026

FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech

Haoxu Wang, Biao Tian, Weiqing Li, Xiang Lv +2 more

This paper presents FlowTTS-GRPO, an online RL framework for Flow-Matching based Text-to-Speech that enables direct fine-tuning of open-source models.

View →
cs.DCcs.LGcs.PFEmpiricalRecentJun 11, 2026

GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving

Xinwei Qiang, Yifan Hu, Shixuan Sun, Jing Yang +5 more

GF-DiT: A policy-programmable runtime for elastic DiT serving

View →
cs.CRcs.LGRecentJun 2, 2026

RogueMerge: Robust and Unified Attacks against LLM Model Merging

Jinghuai Zhang, Yetian He, Kunlin Cai, Han Zhao +2 more

RogueMerge introduces a unified framework to robustly attack LLM model merging by addressing the challenges of autoregressive decoding, unknown merging configurations, and prompt generalization, signi…

View →
cs.AIRecentMay 27, 2026

PRO-CUA: Process-Reward Optimization for Computer Use Agents

Yifei He, Rui Yang, Hao Bai, Tong Zhang +1 more

PRO-CUA introduces a process-reward optimization framework that enables efficient, step-level reinforcement learning for training computer use agents by decoupling environment interaction from policy…

View →
cs.AIRecentMay 27, 2026

PRO-CUA: Process-Reward Optimization for Computer Use Agents

Yifei He, Rui Yang, Hao Bai, Tong Zhang +1 more

PRO-CUA introduces a process-reward optimization framework that enables efficient, step-level reinforcement learning for training computer use agents by decoupling environment interaction from policy…

View →