Jierui Li @ XDU-VT

About Me

I am a final-year undergraduate student in the Xidian University–Virginia Tech Joint Program, majoring in Big Data Management and Application.

My research focuses on Embodied AI, Vision-Language Robot Learning, Long-Horizon Task Reasoning, and Interactive Multimodal Agents. I am particularly interested in developing intelligent agents that can perceive multimodal environments, reason and plan over complex tasks, and interact reliably with the physical world.

I am currently seeking Ph.D. opportunities for Fall 2027. Feel free to reach out for research collaboration or potential opportunities.

Research Interests

Embodied AI: Vision-Language Robot Learning, Physical and Spatial Reasoning
Multimodal Agents: Multimodal Reasoning, Agent Evaluation, Reward Modeling
Long-Horizon Reasoning: Task Planning, Sequential Decision-Making, Interactive Agents

Research Experience

University of Illinois Urbana-Champaign (UIUC), PLAN Lab
Advised by Ismini Lourentzou.
Research on multimodal learning and embodied intelligence.
Virginia Tech
Advised by Xuan Wang.
Research on multimodal reasoning and reliable agentic systems.
Tsinghua University, THUNLP
Advised by Zhiyuan Liu, Xin Yi, Shuning Zhang, and Lingxing Kong.
Research on multimodal reward evaluation and reliable vision-language models.
National University of Singapore (NUS), HPC-AI Lab
Advised by Yang You.
Research on multimodal multi-agent reasoning and group-level Theory of Mind.
University of Science and Technology of China (USTC)
Advised by Zhi Zheng.
Research on online time-series forecasting and fine-grained concept drift modeling.
Xidian University
Advised by Hao Zhu.
Research on parameter-efficient visual adaptation and visual representation learning.

News

[Sep. 2026] 🎉 AssemState was accepted as a poster to the NeurIPS 2026 Workshop on Physical World AI (PhysWorldAI).
[Aug. 2026] 🎉 RouteGraph-Mona was accepted as a full paper to PRICAI 2026.
[Apr. 2026] 🎉 GroupToM-Bench was accepted to ACL 2026 Main Conference (SAC Oral).

Publications

NeurIPS 2026 WS

AssemState: Manual and Physical-State-Guided Reasoning for Zero-Shot Furniture Assembly

Zhiyuan Qi*, Jierui Li*, Yifan Shen, Cheng Qian, Jiateng Liu

NeurIPS 2026 Workshop on Physical World AI (PhysWorldAI), 2026.

PDF Page Poster

* Equal contribution.
ACL 2026

GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs

Weidong Tang, Jierui Li, Yueling Hou, Zihan Mei, Can Zhang, Xinyan Wan, Zhiyuan Liang, Pengfei Zhou, Wangbo Zhao, Yang You

The 64th Annual Meeting of the Association for Computational Linguistics (ACL), 2026.

PDF Page SAC Oral
PRICAI 2026

RouteGraph-Mona: Confusion-Aware Routing Fine-Tuning for Mineral Image Classification

Jierui Li*, Zhiyuan Qi*, Hao Zhu, Yufan Liu, Jixian Liu, Shaojie Jiang, Jianda Wang, Yaqi Liu, Xiaotong Li, Wei Wang

Pacific Rim International Conference on Artificial Intelligence (PRICAI), 2026.

PDF arXiv Full Paper

* Equal contribution.
When A Stays A: Disentangling Training-Free Repair in Spatial MCQA

Jierui Li, Meng Lu, Xuan Wang

Submitted to ACL Rolling Review, October 2026.

Under Review
CueShiftBench: How Heuristic Cues Shape Multimodal Reward Evaluation

Jierui Li, Yueling Hou, Zhiyuan Qi, Bo Zhang, Ziqi Ma, Jixian Liu, Wenyue Ban, Shuning Zhang, Yifan Shen, Weidong Tang, Qian Jiang, Xin Yi, Lingxing Kong

Submitted to ACL Rolling Review, August 2026.

Under Review
FurniReason: Zero-Shot Vision-Language Reasoning for Manual-Guided Furniture Assembly

Zhiyuan Qi*, Jierui Li*, Yifan Shen, Cheng Qian, Jiateng Liu

Submitted to the AAAI Conference on Artificial Intelligence (AAAI), 2027.

Under Review

* Equal contribution.
Fine-Grained Drift Modeling via Unmixed Representations for Online Time Series Forecasting

Jierui Li, Weidong Tang, Jixian Liu, Shuning Zhang, Zhi Zheng, Lingxing Kong

Submitted to the ACM International Conference on Web Search and Data Mining (WSDM).

Under Review
FedOLoRA: Demand-Aware Recycling of Fixed-Capacity Orthogonal Memory for Federated Continual LoRA

Zhuodong Liu*, Jierui Li*, Tianzuo Yuan, Xiangyu Li

Submitted to the AAAI Conference on Artificial Intelligence (AAAI), 2027.

Under Review

* Equal contribution.
CoTAC: Collaborative Contextualization, Tokenization, and Calibration for Multimodal Generative Recommendation

Zhuodong Liu*, Yunhe Ni*, Jierui Li*, Yuchen Zhang, Peiyu Hu

Submitted to the AAAI Conference on Artificial Intelligence (AAAI), 2027.

Under Review

* Equal contribution.
Shape Feature Preservation Network for Building Change Detection

Xiaotong Li, Jianda Wang, Haoyu Wang, Hao Zhu, Jierui Li, Huihui Dong, Biao Hou

Submitted to IEEE Transactions on Geoscience and Remote Sensing.

Under Review