Yuxing Long | 龙宇星

I am a third-year master's student at the School of Artificial Intelligence, Beijing University of Posts and Telecommunications (BUPT). I'm also a research visitor in Center on Frontiers of Computing Studies (CFCS) at Peking University, advised by Prof. Hao Dong.

My research interests include embodied navigation, multimodal pretraining, and multimodal conversation.

Email: longyuxing [at] bupt.edu.cn

Email / Github / Google Scholar

Publications

	Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions Yuxing Long, Xiaoqi Li, Wenzhe Cai, Hao Dong International Conference on Robotics and Automation (ICRA) 2024 Paper / Project / Code DiscussNav agent actively discusses with multiple domain experts before moving.
	Improving Situated Conversational Agents with Step-by-Step Multi-modal Logic Reasoning Yuxing Long, Huibin Zhang, Binyuan Hui, Zhenglu Yang, Caixia Yuan, Xiaojie Wang, Fei Huang, Yongbin Li Champion of SIMMC 2.1 Competition, DSTC 11 Workshop* (Best Paper) Paper / Code We propose a dual-system framework to conduct multimodal logic reasoning step-by-step.
	Whether you can locate or not? Interactive Referring Expression Generation Fulong Ye, Yuxing Long, Fangxiang Feng, Xiaojie Wang ACM Multimedia (MM) 2023 Paper / Code We generate referring expressions by multi-round communications.
	Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark Yuxing Long, Binyuan Hui, Caixia Yuan, Fei Huang, Yongbin Li, Xiaojie Wang Findings of the Association for Computational Linguistics (Findings of ACL) 2023 Paper A new dataset for multimodal recommendation dialog with subjective preferences.
	SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph Yuxing Long, Binyuan Hui, Fulong Ye, Yanyang Li, Zhuoxin Han, Caixia Yuan, Yongbin Li, Xiaojie Wang AAAI Conference on Artificial Intelligence 2023 (Oral presentation) Paper / Code We improve the situated conversation agent through novel multimodal question-answering pretraining tasks.

Services

Reviewer: ACM MM 2023
Reviewer: NeurIPS 2023 Self-Supervised Learning - Theory and Practice Workshop
Reviewer: NeurIPS 2022 Human in the Loop Learning (HiLL) Workshop

Selected Awards and Honors

National Scholarship, 2023
Excellent Graduate, Beijing University of Posts and Telecommunications, 2023