Yunxiao Wang

Yunxiao Wang

Ph.D. Candidate of Artificial Intelligence

Shandong University

Biography

My name is Yunxiao Wang (王蕴潇). I am a Ph.D. candidate at the School of Software, Shandong University, Jinan, China, advised by Prof. Liqiang Nie and Prof. Meng Liu. Since February 2026 I have been a visiting research student at the CoAgent Lab, Singapore Management University, hosted by Prof. Lizi Liao. My research covers multimodal large language models, affective computing and conversational AI. I obtained my M.S. degree from Shandong University in 2022 and my B.S. degree from China University of Petroleum (East China) in 2019.

Interests
  • Multimodal Large Language Models
  • Affective Computing
  • Conversational AI
  • Information Retrieval
Education
  • Ph.D in Artificial Intelligence, Sep 2022 - Now

    School of Software, Shandong University

  • M.S in Computer Technology, Sep 2019 - Jun 2022

    School of Computer Science and Technology, Shandong University

  • B.S in Internet of Things Engineering, Sep 2015 - Jun 2019

    School of Computer Science and Technology, China University of Petroleum (East China)

Experience

 
 
 
 
 
CoAgent Lab, Singapore Management University
Visiting Research Student
CoAgent Lab, Singapore Management University
February 2026 – Present Singapore
I work on conversational personality assessment, and on KakiPal, an AI learning companion that pairs Socratic tutoring with camera-free affect sensing. KakiPal is in production and in use in university teaching.
 
 
 
 
 
Foundation Model & Applications Department, Kuaishou Technology
Research Intern
Foundation Model & Applications Department, Kuaishou Technology
July 2024 – December 2025 Beijing, China
I worked on video large language models, covering temporal-sensitive instruction tuning with a shortcut-filtered benchmark for temporal understanding (AAAI 2026, Oral), and an agentic thinking-with-videos framework that unifies temporal grounding with question answering (ICML 2026).
 
 
 
 
 
Member, Cooperation Project with Zhiyang Innovation Technology Co., Ltd.
Lightweight Detection of Hidden Dangers in Transmission Line
Member, Cooperation Project with Zhiyang Innovation Technology Co., Ltd.
June 2019 – February 2020 Qingdao, China
I built a lightweight detector for transmission-line inspection, pairing ShuffleNet and MobileNet feature extractors with a Faster R-CNN framework.
 
 
 
 
 
Data Analysis Intern, Weichai Power Co., LTD
Product Nameplate Text Recognition
Data Analysis Intern, Weichai Power Co., LTD
October 2018 – May 2019 Weifang, China
I detected and recognised irregularly arranged text on product nameplates with EAST and CTPN detection and CRNN recognition, automating product-information entry.

Publications

VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
ICML 2026
VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs
AAAI 2026 (Oral)
TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs
A survey on video moment localization
ACM CSUR 2023
A survey on video moment localization
Siamese alignment network for weakly supervised video moment retrieval
IEEE TMM 2023
Siamese alignment network for weakly supervised video moment retrieval

Patents & Standards

Chinese invention patents:

  • CN113590881B — Video clip retrieval and retrieval-model training
  • CN117271743B — Multimodal dialogue emotion recognition
  • CN118898797B — Commonsense-enhanced candidate generation for video action segments
  • CN119670896B — Temporally enhanced video question answering
  • CN120747839B — User behaviour prediction for smart homes
  • CN120805980A — Quantized multimedia question answering for smart-home edge devices (under examination)

Standards, as a co-drafter:

  • SJ/T 12100-2026 — Industrial AI vision online inspection systems for the power industry (industry standard, 2026)
  • T/CESA 1298-2023 / T/CES 247-2023 — Industrial AI vision online inspection systems for transmission lines (group standard, 2023)

Professional Services

Conference reviewer for:

  • AAAI Conference on Artificial Intelligence (AAAI)
  • ACM International Conference on Multimedia (ACM MM)
  • Annual Meeting of the Association for Computational Linguistics (ACL)
  • Conference on Neural Information Processing Systems (NeurIPS)

Journal reviewer for:

  • IEEE Transactions on Knowledge and Data Engineering
  • IEEE Transactions on Circuits and Systems for Video Technology
  • IEEE Transactions on Multimedia
  • Information Sciences

Honors & Awards

  • First Prize of Graduate Academic Scholarship (2023)
  • Second Prize of Graduate Freshmen Scholarship (2022)
  • Third Prize of Graduate Academic Scholarship (2020-2021)
  • First Prize of Graduate Freshmen Scholarship (2019)
  • Excellent Graduate of China University of Petroleum (East China) (2019)
  • National Second Prize of the 14th “Bochuang” Cup National College Students Embedded Design Competition (2018)
  • Third Prize of the 13th National College Students “NXP” Cup Intelligent Car Competition in Shandong Region (2018)
  • First Prize of Academic Scholarship (2018)
  • First Prize of the 12th National College Students “NXP” Cup Intelligent Car Competition in Shandong Region (2017)
  • Second Prize of the 15th Shandong University Students Software Design Competition (2017)
  • “Outstanding Achievements in Scientific and Technological Contributions” Scholarship (2017)
  • Third Prize of Academic Scholarship (2017)
  • “Shengli Oil Talent” Scholarship (2016)

Contact