Yunxiang Mo

Yunxiang Mo

Undergraduate researcher in NLP at HKUST. Advised by Prof. Yangqiu Song.

Posts by Collection

portfolio

publications

DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay

Published in EMNLP 2025 Workshop (Spotlight), 2025

EMNLP 2025 Workshop (Spotlight). The original version of DixitWorld; an extended version was later accepted to ACL 2026 Main Conference.

Recommended citation: Yunxiang Mo, Tianshi Zheng, Qing Zong, Jiayu Liu, Baixuan Xu, Yauwai Yim, Chunkit Chan, Jiaxin Bai, Yangqiu Song. (2025). "DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay." EMNLP 2025 Workshop (Spotlight).
Download Paper

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

Published in ICLR 2026 (Oral), 2026

A scaled-up open-source framework for computer use agents, with a large dataset spanning 6 operating systems and 3 task domains. ICLR 2026 Oral.

Recommended citation: Zhaoyang Liu, Jingjing Xie, Zichen Ding, Zehao Li, Bowen Yang, Zhenyu Wu, Xuehui Wang, Qiushi Sun, Shi Liu, Weiyun Wang, Shenglong Ye, Qingyun Li, Xuan Dong, Yue Yu, Chenyu Lu, Yunxiang Mo, Yao Yan, Zeyue Tian, Xiao Zhang, Yuan Huang, Yiqian Liu, Weijie Su, Gen Luo, Xiangyu Yue, Biqing Qi, Kai Chen, Bowen Zhou, Yu Qiao, Qifeng Chen, Wenhai Wang. (2026). "ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data." ICLR 2026 (Oral).
Download Paper

DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay

Published in ACL 2026 (Main Conference), 2026

Extended version of the EMNLP 2025 Workshop paper, accepted at ACL 2026 Main Conference. Adds a third difficulty tier (252 questions total), a 72B-scale ablation, and calibration/sensitivity analyses.

Recommended citation: Yunxiang Mo, Tianshi Zheng, Qing Zong, Jiayu Liu, Baixuan Xu, Yauwai Yim, Chunkit Chan, Jiaxin Bai, Yangqiu Song. (2026). "DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay." Proceedings of ACL 2026 (Main Conference).
Download Paper

talks

teaching