Publications 🌟

Here are some representative publications I've worked on. As I'm new to many fields, I will strive to contribute more in the future. The most up-to-date publication list can be found in my Google Scholar site. I wish that one day this page will be full and shining with accomplishments.

Full lists

Conference	Publication
CVPR 2026	Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory Website Paper Code Data Ce Zhang^, Jinxi He^, Junyi He, Katia P. Sycara, Yaqi Xie
Arxiv	Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning Paper Code Jing Bi, Susan Liang, Xiaofei Zhou, Pinxin Liu, Jinxi He, Junjia Guo, Yunlong Tang, Luchuan Song, Chao Huang, Ali Vosoughi, Guangyu Sun, Jiarui Wu, Shu Yang, Daoan Zhang, Chen Chen, Lianggong Bruce Wen, Zhang Liu, Jiebo Luo, Chenliang Xu
AAAI 2026	Caption Anything in Video: Fine-grained Object-centric Captioning via Spatio-temporal Multimodal Prompting Paper Code Yunlong Tang, Jing Bi, Chao Huang, Susan Liang, Daiki Shimada, Hang Hua, Yunzhong Xiao, Yizhi Song, Pinxin Liu, Mingqian Feng, Jinxi He, Junjia Guo, Zhuo Liu, Luchuan Song, Ali Vosoughi, Liu He, Zeliang Zhang, Jiebo Luo, Chenliang Xu
Arxiv	A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity Paper Website Jing Bi, Junjia Guo, Susan Liang, Guangyu Sun, Luchuan Song, Yunlong Tang, Jinxi He, Jiarui Wu, Ali Vosoughi, Chen Chen, Chenliang Xu
ICCV 2025 Workshop	VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results Paper Dasong Li, Sizhuo Ma, Hang Hua, …, Luchuan Song, Jinxi He, Jiarui Wu, Hanjia Lyu
Frontiers in Public Health	Public perceptions and discussions of synthetic nicotine on Twitter Paper Jinxi He^, Jiarui Chen^, Zidian Xie, Dongmei Li

^* Equal contribution