Han Zhao
6 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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 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 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: A policy-programmable runtime for elastic DiT serving
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.
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.
Papers
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…