activity
20242026
collaborators

7 papers

cs.LG2026

VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training

Dingwei Zhu, Shihan Dou, Zhiheng Xi +16

Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete reward supervision, which undermines policy stability and generalization. Such noi…

cs.LG2026

DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training

Dingwei Zhu, Zhiheng Xi, Shihan Dou +17

Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain (OOD) generalization, especially in LLM…

cs.LG2026

DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training

Dingwei Zhu, Zhiheng Xi, Shihan Dou +15

Reinforcement learning (RL) has shown strong performance in LLM post-training, but real-world deployment often involves noisy or incomplete supervision. In such settings, complex a…

cs.SD2025

From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modeling

Yifei Cao, Changhao Jiang, Jiabao Zhuang +11

Assessing the perceptual quality of synthetic speech is crucial for guiding the development and refinement of speech generation models. However, it has traditionally relied on huma…

cs.HC2025

MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning

Liujian Tang, Shaokang Dong, Yijia Huang +21

This paper presents MagicGUI, a foundational mobile GUI agent designed to address critical challenges in perception, grounding, and reasoning within real-world mobile GUI environme…

cs.CL2025

Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition

Yuming Yang, Wantong Zhao, Caishuang Huang +11

Open Named Entity Recognition (NER), which involves identifying arbitrary types of entities from arbitrary domains, remains challenging for Large Language Models (LLMs). Recent stu…