Qian Jiang

Hi, nice to meet you! I am an incoming M.S. student in Computer Science and Technology at Peking University Shenzhen Graduate School. My research interests include multimodal foundation models,trustworthy AI, vision-language models, AI agents, and embodied AI.

Email  /  CV  /  中文简历  /  Google Scholar  /  GitHub  /  Zhihu

Peking UniversityNortheastern University Huizhou and Shenzhen, Guangdong, China

profile photo
News
  • [2026.09] Admitted to the M.S. program in Computer Science at Peking University Shenzhen Graduate School.
  • [2026.05] Received Finalist recognition in the 2026 Mathematical Contest in Modeling (top 0.1%-2%).
  • [2026.04] Two papers were accepted to ACL 2026.
  • [2026.03] One paper was accepted as an Oral presentation at ICME 2026.
  • [2025.11] One paper was accepted to AAAI 2026.
Research

My research interests, in order, are:

  1. Multimodal LLMs
  2. Trustworthy AI
  3. AI Agents and Embodied AI
* denotes equal contribution. Selected publications are listed below.
Representative figure from Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models
Zirui Song*, Qian Jiang*, et al.
ACL 2026 Main · Co-first author, CCF-A
Paper

An open benchmark and perturbation toolbox for systematically evaluating jailbreak vulnerabilities in large audio-language models.

Representative figure from OmniFood-Bench: Evaluating VLMs for Nutrient Reasoning and Personalized Health Advice
OmniFood-Bench: Evaluating VLMs for Nutrient Reasoning and Personalized Health Advice
Qian Jiang, Zhecheng Shi, et al.
ICME 2026 Oral · First author, CCF-B
Paper

A progressive benchmark for food perception, quantitative nutrition reasoning, and safety-critical personalized dietary advice.

Representative figure from ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models
ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models
Zirui Song*, Guanghan Ouyang*, ... Qian Jiang ..., et al.
AAAI 2026 · Contributing author, CCF-A
Paper

A reinforcement-learning framework for affordance reasoning and trajectory prediction in embodied manipulation.

Representative figure from FineState-Bench: Benchmarking State-Conditioned Grounding for Fine-grained GUI State Setting
FineState-Bench: Benchmarking State-Conditioned Grounding for Fine-grained GUI State Setting
Fengxian Ji*, Jingpu Yang*, Zirui Song*, Yuanxi Wang, Zhexuan Cui, Yuke Li, Qian Jiang, Xiuying Chen
ACL 2026 Findings · Contributing author, CCF-A
Paper

A benchmark for fine-grained, state-conditioned GUI grounding with exact goal-state verification and visual diagnosis.

Research Experience

Mohamed bin Zayed University of Artificial Intelligence, advised by Prof. Xiuying Chen

Conduct research on trustworthy AI, including multimodal LLM jailbreak attacks and reliable AI-generated text detection.

Language and Intelligent Systems Lab, Northeastern University, advised by Prof. Miao Fang

Conduct research on VLMs and agents; serve as the lead student coordinator for laboratory recruiting and operations.

Education

Peking University 2027.09 - 2030.06

M.S. in Computer Science
Admitted

Northeastern University 2023.09 - 2027.06

B.Eng. in Computer Science and Technology
GPA: 4.19/5.00 (5/196, top 2.56%); CET-4: 579, CET-6: 528; Selected coursework: Calculus I/II (99), Probability Theory (100), Optimization (97), Linear Algebra (92)

Honors & Activities
  • 2026 Mathematical Contest in Modeling Finalist (top 0.1%-2%)
  • Third Prize, National Final of the Global AI Algorithm Elite Competition
  • Technical blog: https://www.zhihu.com/people/bu-neng-yao-gong
  • Student lead, undergraduate academic community: https://neuqnlp.github.io/team
  • Personal Page:https://pbrqianjiang.github.io/

Last updated on September 29, 2026.