Harris (Jianrui) Zhang

Publications

• 
  Reasoning-Augmented Representations for Multimodal Retrieval

  Jianrui Zhang*, Anirudh Sundara Rajan*, Brandon Han, Soochahn Lee, Sukanta Ganguly, Yong Jae Lee

  arXiv, 2026

  [arXiv] [Code]

• 
  Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding

  Christopher Clark*, Jieyu Zhang*, Zixian Ma*, ..., Jianrui Zhang, ..., Ali Farhadi, Ranjay Krishna

  The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

  [Tech Report] [Blog] [Code] [Models] [Datasets]

• 
  Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos

  Jianrui Zhang*, Mu Cai*, Yong Jae Lee

  Recommended Accept by ACs of the NeurIPS D&B, 2025

  [OpenReview] [arXiv] [Project Page] [Code] [Dataset] [Leaderboard]

• 
  CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples

  Jianrui Zhang*, Mu Cai*, Tengyang Xie, Yong Jae Lee

  Findings of the Association for Computational Linguistics (ACL Findings), 2024

  Trewartha Senior Honors Thesis Research Award

  [arXiv] [Project Page] [Code] [Dataset]

• 
  TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models

  Mu Cai, Reuben Tan, Jianrui Zhang, Bocheng Zou, ..., Jaden Park, Jianfeng Gao^, Yong Jae Lee^, Jianwei Yang^

  arXiv, 2024

  [arXiv] [Project Page] [Code] [Dataset] [Leaderboard]

• 
  VGBench: Evaluating Large Language Models on Vector Graphics Understanding and Generation

  Bocheng Zou*, Mu Cai*, Jianrui Zhang, Yong Jae Lee

  Conference on Empirical Methods in Natural Language Processing (EMNLP Main), 2024

  [arXiv] [Project Page] [Code] [Datasets]

• 
  The Implementation of a Communication Deadlock Analysis Based on the Theory of Deadlock Analysis for the Actor Model

  Yupeng Xi, Jianrui Zhang, Furi Xiang, (Jonathan Aldrich)

  Journal of Software Engineering and Applications (JSEA), 2019, 12, 393-405

  [Journal Page]

Teaching

• CS 639: Deep Learning for Computer Vision (Spring 2025 TA)

Fun Facts

I was born in Shanghai, China, yet I have only been to around 5 other Chinese cities throughout my first 18 years of living, until I left China for the US. I have in fact been to far more cities abroad than in China.

I am very interested in history and geopolitics, partly related to my passion for grand strategy games such as Civilization, Crusader Kings, Europa Universalis, Hearts of Iron, Victoria, and Stellaris. This also makes me fascinate the many cities with rich histories and fuels me to travel around the world.

I also enjoy a wide variety of manga, anime, and visual novels. Thanks to this hobby, I became passionate about the Japanese language and culture, making me a trilingual (in Chinese, English, and Japanese).