Linfeng Zhou — accepted AI-conference papers

2026

ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence On Mobile Devices

Dezhi Kong, Zhengzhao Feng, Qiliang Liang, Hao Wang, Haofei Sun, Changpeng Yang +9

CVPR 2026

Multimodal large language models (MLLMs) have made significant progress in mobile agent development, yet their capabilities are predominantly confined to a reactive paradigm, where they merely execute explicit user commands. The emerging paradigm of proactive intelligence, where agents autonomously

Cited by 0 Source ↗code ↗Scholar ↗

2025

MWPO: Enhancing LLMs Performance through Multi-Weight Preference Strength and Length Optimization

Shiyue Xu, Fu Zhang, Jingwei Cheng, Linfeng Zhou

ACL 2025finding

Direct Preference Optimization (DPO) have proposed offline alternatives to Reinforcement Learning from Human Feedback (RLHF). In DPO, each preference pair, which serves as the foundation for learning, is typically constructed by first generating multiple responses to the same instruction and then an…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗