6 papers
DocPO: Advancing Document Policy Optimization via Tailored Step-Aware Rewards
Yunhao Wang, Binghong Wu, Zhenyu Huang +4
Reinforcement learning (RL) for document parsing often relies on reference-based rewards rooted in edit distance (e.g., tree edit distance), yet it remains hard to optimize in the…
MORE: A Multilingual Document Parsing Benchmark and Evaluation
Long Xu, Binghong Wu, Tinghao Yu +6
Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machine-readable formats is critica…
Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild
Mao Zheng, Zheng Li, Tao Chen +10
Hy-MT2 is a family of fast-thinking multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of wh…
WRAP++: Web discoveRy Amplified Pretraining
Jiang Zhou, Yunhao Wang, Xing Wu +2
Synthetic data rephrasing has emerged as a powerful technique for enhancing knowledge acquisition during large language model (LLM) pretraining. However, existing approaches operat…
ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex Reasoning
Yunhao Wang, Ziting Li, Shuai Chen +6
Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms,…
Adaptive Deep Reasoning: Triggering Deep Thinking When Needed
Yunhao Wang, Yuhao Zhang, Tinghao Yu +3
Large language models (LLMs) have shown impressive capabilities in handling complex tasks through long-chain reasoning. However, the extensive reasoning steps involved can signific…