Hejie Cui
Logo Senior Research Scientist, Google

I am a Senior Research Scientist at Google. My research develops AI self-evolving agents that improve through multi-turn interaction, adaptive learning, and rigorous evaluation, with a focus on reliable self-improvement and efficient long-horizon reasoning.

Before joining industry, I was a Postdoctoral Researcher at Stanford University, advised by Prof. Nigam H. Shah and Prof. Sanmi Koyejo, where I developed evaluation methods and data foundations for clinical AI. I received my Ph.D. in Computer Science from Emory University, advised by Prof. Carl Yang, and my B.Eng. in Software Engineering from Tongji University as Valedictorian (GPA 4.9/5.0, Rank 1/164). During undergrad, I worked with Prof. Tianwei Yu on machine learning research and interned at the Perk Lab with Prof. Gabor Fichtinger at Queen's University.


Education
  • Stanford University
    Postdoctoral Researcher
    2024 - 2025
  • Emory University
    Ph.D. in Computer Science
    2019 - 2024
  • Tongji University
    B.Eng. in Software Engineering
    2015 - 2019
Experience
  • Google
    Senior Research Scientist
    2026 - Present
  • Amazon Rufus (Foundation Model Training)
    Applied Scientist
    2025 - 2026
  • Microsoft Research
    Research Intern
    Summer 2023
  • Amazon
    Applied Scientist Intern
    Summer 2022
Honors & Awards
News
2026
Our paper Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning was accepted to NeurIPS 2026 and the COLM 2026 Workshop on Efficient Reasoning.
Sep
MatrAIx: Simulating the World with 8.3 Billion Persona Agents is online!
Aug
HeaPA was accepted to COLM 2026.
Jul
Received the ICML 2026 Silver Reviewer Award.
May
T2PO was accepted to ICML 2026 as a Spotlight paper.
May
Joined Google as a Senior Research Scientist.
Apr
2025
OpenAI used MedHELM as a medical evaluation benchmark for clinical-scenario model evaluation.
Dec
MedHELM was published in Nature Medicine.
Dec
As proposal lead for CuraBench, I secured $100K in funding from Stanford RAISE Health and Stanford HAI.
Jun
2024
Served as Junior Chair for the Large Models and Multimodal AI Roundtable at ML4H 2024.
Dec
Selected as a Rising Star at the Michigan AI Symposium.
Oct
Our survey on LLM domain specialization was cited in the 2024 Economic Report of the President.
Mar
2023
Selected as an EECS Rising Star 2023.
Oct
Selected Publications (view all )
Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning

Xintong Li, Sha Li, Rongmei Lin, Hongye Jin, Linwei Li, Hejie Cui, Sarah Zhang, Chia-Yuan Chang, Kewei Cheng, Besnik Fetahu, Priyanka Nigam, Jingbo Shang, Bing Yin

The Conference on Neural Information Processing Systems (NeurIPS); also accepted to the COLM 2026 Workshop on Efficient Reasoning. 2026

We introduce Step-wise Adaptive Penalization (SWAP), a fine-grained reinforcement learning framework that dynamically allocates length penalties to low-importance reasoning steps based on their contribution to the correct answer. SWAP reduces reasoning length while improving accuracy, without relying on external reward models or heuristic budgets.

Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning

Xintong Li, Sha Li, Rongmei Lin, Hongye Jin, Linwei Li, Hejie Cui, Sarah Zhang, Chia-Yuan Chang, Kewei Cheng, Besnik Fetahu, Priyanka Nigam, Jingbo Shang, Bing Yin

The Conference on Neural Information Processing Systems (NeurIPS); also accepted to the COLM 2026 Workshop on Efficient Reasoning. 2026

We introduce Step-wise Adaptive Penalization (SWAP), a fine-grained reinforcement learning framework that dynamically allocates length penalties to low-importance reasoning steps based on their contribution to the correct answer. SWAP reduces reasoning length while improving accuracy, without relying on external reward models or heuristic budgets.

T²PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
T²PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning

Haixin Wang, Hejie Cui#, Chenwei Zhang, Xin Liu, Shuowei Jin, Shijie Geng, Xinyang Zhang, Nasser Zalmout, Zhenyu Shi, Yizhou Sun (# corresponding author)

The International Conference on Machine Learning (ICML) 2026 Spotlight

Recent progress in multi-turn reinforcement learning (RL) has significantly improved reasoning LLMs' performances on complex interactive tasks. Despite advances in stabilization techniques such as fine-grained credit assignment and trajectory filtering, instability remains pervasive and often leads to training collapse.

T²PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning

Haixin Wang, Hejie Cui#, Chenwei Zhang, Xin Liu, Shuowei Jin, Shijie Geng, Xinyang Zhang, Nasser Zalmout, Zhenyu Shi, Yizhou Sun (# corresponding author)

The International Conference on Machine Learning (ICML) 2026 Spotlight

Recent progress in multi-turn reinforcement learning (RL) has significantly improved reasoning LLMs' performances on complex interactive tasks. Despite advances in stabilization techniques such as fine-grained credit assignment and trajectory filtering, instability remains pervasive and often leads to training collapse.

HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning
HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

Weiqi Wang, Xin Liu, Binxuan Huang, Hejie Cui, Rongzhi Zhang, Changlong Yu, Shuowei Jin, Jingfeng Yang, Qingyu Yin, Zhengyang Wang, Zheng Li, Yifan Gao, Priyanka Nigam, Bing Yin, Lihong Li, Yangqiu Song

The Conference on Language Modeling (COLM) 2026

RLVR is now a standard way to train LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency depends heavily on which prompts you sample and when. We introduce HeaPA, a query-side RLVR framework that combines difficulty-aware heap-based frontier sampling with on-policy query augmentation to improve math reasoning efficiency and accuracy.

HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

Weiqi Wang, Xin Liu, Binxuan Huang, Hejie Cui, Rongzhi Zhang, Changlong Yu, Shuowei Jin, Jingfeng Yang, Qingyu Yin, Zhengyang Wang, Zheng Li, Yifan Gao, Priyanka Nigam, Bing Yin, Lihong Li, Yangqiu Song

The Conference on Language Modeling (COLM) 2026

RLVR is now a standard way to train LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency depends heavily on which prompts you sample and when. We introduce HeaPA, a query-side RLVR framework that combines difficulty-aware heap-based frontier sampling with on-policy query augmentation to improve math reasoning efficiency and accuracy.

CoMem: Context Management with A Decoupled Long-Context Model
CoMem: Context Management with A Decoupled Long-Context Model

Yuwei Zhang, Chengyu Dong, Shuowei Jin, Changlong Yu, Hejie Cui, Hongye Jin, Xinyang Zhang, Hamed Bonab, Colin Lockard, Jianshu Chen, Zhenyu Shi, Jingbo Shang, Xian Li, Bing Yin

The International Conference on Machine Learning (ICML) 2026

Context management enables agentic models to solve long-horizon tasks through iterative summarization of previous interaction histories. However, this process typically incurs substantial decoding overhead for the extra summarization tokens, which significantly affect the end-to-end response latency at deployment.

CoMem: Context Management with A Decoupled Long-Context Model

Yuwei Zhang, Chengyu Dong, Shuowei Jin, Changlong Yu, Hejie Cui, Hongye Jin, Xinyang Zhang, Hamed Bonab, Colin Lockard, Jianshu Chen, Zhenyu Shi, Jingbo Shang, Xian Li, Bing Yin

The International Conference on Machine Learning (ICML) 2026

Context management enables agentic models to solve long-horizon tasks through iterative summarization of previous interaction histories. However, this process typically incurs substantial decoding overhead for the extra summarization tokens, which significantly affect the end-to-end response latency at deployment.

EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs
EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs

Yuzhang Xie, Keqi Han, Yunpeng Xiao, Hejie Cui, Guanchen Wu, Ziyang Zhang, Kai Shu, Jiaying Lu, Xiao Hu, Carl Yang

The ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Datasets and Benchmarks Track 2026 Oral

Clinical decision-making (CDM) is central to real-world clinical workflows, where clinicians infer diagnoses, select treatments, or anticipate future health outcomes under incomplete evidence. EHRBench is an automated and reliable EHR-grounded benchmark for evaluating LLM-based clinical decision-making at scale. It constructs nearly 1M QA items spanning diagnosis, treatment, and prognosis, and benchmarks more than 30 representative LLMs to reveal actionable gaps toward clinically reliable LLM systems.

EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs

Yuzhang Xie, Keqi Han, Yunpeng Xiao, Hejie Cui, Guanchen Wu, Ziyang Zhang, Kai Shu, Jiaying Lu, Xiao Hu, Carl Yang

The ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Datasets and Benchmarks Track 2026 Oral

Clinical decision-making (CDM) is central to real-world clinical workflows, where clinicians infer diagnoses, select treatments, or anticipate future health outcomes under incomplete evidence. EHRBench is an automated and reliable EHR-grounded benchmark for evaluating LLM-based clinical decision-making at scale. It constructs nearly 1M QA items spanning diagnosis, treatment, and prognosis, and benchmarks more than 30 representative LLMs to reveal actionable gaps toward clinically reliable LLM systems.

MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks
MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks

Suhana Bedi*, Hejie Cui*, Miguel Fuentes*, Alyssa Unell*, Michael Wornow, Juan M. Banda, Nikesh Kotecha, Timothy Keyes, Yifan Mai, Mert Oez, Hao Qiu, Shrey Jain, Leonardo Schettini, Mehr Kashyap, Jason Alan Fries, Akshay Swaminathan, Philip Chung, Fateme Nateghi Haredasht, Ivan Lopez, Asad Aali, Gabriel Tse, Ashwin Nayak, Shivam Vedak, Sneha S. Jain, Birju Patel, Oluseyi Fayanju, Shreya Shah, Ethan Goh, Dong-han Yao, Brian Soetikno, Eduardo Reis, Sergios Gatidis, Vasu Divi, Robson Capasso, Rachna Saralkar, Chia-Chun Chiang, Jenelle Jindal, Tho Pham, Faraz Ghoddusi, Steven Lin, Albert S. Chiou, Christy Hong, Mohana Roy, Michael F. Gensheimer, Hinesh Patel, Kevin Schulman, Dev Dash, Danton Char, Lance Downing, Francois Grolleau, Kameron Black, Bethel Mieso, Aydin Zahedivash, Wen-wai Yim, Harshita Sharma, Tony Lee, Hannah Kirsch, Jennifer Lee, Nerissa Ambers, Carlene Lugtu, Aditya Sharma, Bilal Mawji, Alex Alekseyev, Vicky Zhou, Vikas Kakkar, Jarrod Helzer, Anurang Revri, Yair Bannett, Roxana Daneshjou, Jonathan Chen, Emily Alsentzer, Keith Morse, Nirmal Ravi, Nima Aghaeepour, Vanessa Kennedy, Akshay Chaudhari, Thomas Wang, Sanmi Koyejo, Matthew P. Lungren, Eric Horvitz, Percy Liang, Michael A. Pfeffer, Nigam H. Shah (* equal contribution)

Nature Medicine (5-Year Impact Factor: 52.4) 2026

Large language models (LLMs) achieve near-perfect scores on medical licensing exams, yet these benchmarks fail to capture the complexity of real-world clinical practice.

MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks

Suhana Bedi*, Hejie Cui*, Miguel Fuentes*, Alyssa Unell*, Michael Wornow, Juan M. Banda, Nikesh Kotecha, Timothy Keyes, Yifan Mai, Mert Oez, Hao Qiu, Shrey Jain, Leonardo Schettini, Mehr Kashyap, Jason Alan Fries, Akshay Swaminathan, Philip Chung, Fateme Nateghi Haredasht, Ivan Lopez, Asad Aali, Gabriel Tse, Ashwin Nayak, Shivam Vedak, Sneha S. Jain, Birju Patel, Oluseyi Fayanju, Shreya Shah, Ethan Goh, Dong-han Yao, Brian Soetikno, Eduardo Reis, Sergios Gatidis, Vasu Divi, Robson Capasso, Rachna Saralkar, Chia-Chun Chiang, Jenelle Jindal, Tho Pham, Faraz Ghoddusi, Steven Lin, Albert S. Chiou, Christy Hong, Mohana Roy, Michael F. Gensheimer, Hinesh Patel, Kevin Schulman, Dev Dash, Danton Char, Lance Downing, Francois Grolleau, Kameron Black, Bethel Mieso, Aydin Zahedivash, Wen-wai Yim, Harshita Sharma, Tony Lee, Hannah Kirsch, Jennifer Lee, Nerissa Ambers, Carlene Lugtu, Aditya Sharma, Bilal Mawji, Alex Alekseyev, Vicky Zhou, Vikas Kakkar, Jarrod Helzer, Anurang Revri, Yair Bannett, Roxana Daneshjou, Jonathan Chen, Emily Alsentzer, Keith Morse, Nirmal Ravi, Nima Aghaeepour, Vanessa Kennedy, Akshay Chaudhari, Thomas Wang, Sanmi Koyejo, Matthew P. Lungren, Eric Horvitz, Percy Liang, Michael A. Pfeffer, Nigam H. Shah (* equal contribution)

Nature Medicine (5-Year Impact Factor: 52.4) 2026

Large language models (LLMs) achieve near-perfect scores on medical licensing exams, yet these benchmarks fail to capture the complexity of real-world clinical practice.

Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey
Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey

Chen Ling, Xujiang Zhao, Jiaying Lu, Chengyuan Deng, Can Zheng, Junxiang Wang, Tanmoy Chowdhury, Yun Li, Hejie Cui, Xuchao Zhang, Tianjiao Zhao, Amit Panalkar, Dhagash Mehta, Stefano Pasquali, Wei Cheng, Haoyu Wang, Yanchi Liu, Zhengzhang Chen, Haifeng Chen, Chris White, Quanquan Gu, Jian Pei, Carl Yang, Liang Zhao

ACM Computing Surveys (5-Year Impact Factor: 31.4) 2025

This survey presents a taxonomy of domain-specialization techniques for large language models, covering external augmentation, prompt crafting, and model fine-tuning across a broad range of application domains.

Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey

Chen Ling, Xujiang Zhao, Jiaying Lu, Chengyuan Deng, Can Zheng, Junxiang Wang, Tanmoy Chowdhury, Yun Li, Hejie Cui, Xuchao Zhang, Tianjiao Zhao, Amit Panalkar, Dhagash Mehta, Stefano Pasquali, Wei Cheng, Haoyu Wang, Yanchi Liu, Zhengzhang Chen, Haifeng Chen, Chris White, Quanquan Gu, Jian Pei, Carl Yang, Liang Zhao

ACM Computing Surveys (5-Year Impact Factor: 31.4) 2025

This survey presents a taxonomy of domain-specialization techniques for large language models, covering external augmentation, prompt crafting, and model fine-tuning across a broad range of application domains.

TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records
TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records

Hejie Cui*, Alyssa Unell*, Bowen Chen, Jason Alan Fries, Emily Alsentzer, Sanmi Koyejo, Nigam H. Shah (* equal contribution)

npj Digital Medicine (5-Year Impact Factor: 17.0) 2025

Electronic health records (EHRs) contain rich longitudinal information essential for clinical decision-making, yet large language models (LLMs) struggle to reason across patient timelines. We introduce TIMER (Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records), a method to improve LLMs' temporal reasoning over multi-visit EHRs through temporal instruction modeling and evaluation.

TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records

Hejie Cui*, Alyssa Unell*, Bowen Chen, Jason Alan Fries, Emily Alsentzer, Sanmi Koyejo, Nigam H. Shah (* equal contribution)

npj Digital Medicine (5-Year Impact Factor: 17.0) 2025

Electronic health records (EHRs) contain rich longitudinal information essential for clinical decision-making, yet large language models (LLMs) struggle to reason across patient timelines. We introduce TIMER (Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records), a method to improve LLMs' temporal reasoning over multi-visit EHRs through temporal instruction modeling and evaluation.

CuraBench: A Benchmark Dataset Generation System for Healthcare AI Evaluation
CuraBench: A Benchmark Dataset Generation System for Healthcare AI Evaluation

Hejie Cui, Alyssa Unell, Haoran Zhang, Caleb Winston, Jason Alan Fries, Sanmi Koyejo, Nigam H. Shah

KDD 2025 HealthDay Blue Sky Ideas Track 2025

Ensuring that artificial intelligence (AI) tools in healthcare operate safely and effectively requires robust evaluation within realistic clinical contexts. Traditional evaluation methods often rely on standardized benchmarks that fail to capture the full complexity of patient care, while manually curating a dataset for a specific deployment scenario can be time-consuming and limiting.

CuraBench: A Benchmark Dataset Generation System for Healthcare AI Evaluation

Hejie Cui, Alyssa Unell, Haoran Zhang, Caleb Winston, Jason Alan Fries, Sanmi Koyejo, Nigam H. Shah

KDD 2025 HealthDay Blue Sky Ideas Track 2025

Ensuring that artificial intelligence (AI) tools in healthcare operate safely and effectively requires robust evaluation within realistic clinical contexts. Traditional evaluation methods often rely on standardized benchmarks that fail to capture the full complexity of patient care, while manually curating a dataset for a specific deployment scenario can be time-consuming and limiting.

A Review on Knowledge Graphs for Healthcare: Resources, Applications, and Promises
A Review on Knowledge Graphs for Healthcare: Resources, Applications, and Promises

Hejie Cui*, Jiaying Lu*, Ran Xu*, Shiyu Wang, Wenjing Ma, Yue Yu, Shaojun Yu, Xuan Kan, Chen Ling, Liang Zhao, Zhaohui S. Qin, Joyce C. Ho, Tianfan Fu, Jing Ma, Mengdi Huai, Fei Wang, Carl Yang (* equal contribution)

Journal of Biomedical Informatics (JBI) (5-Year Impact Factor: 7.7) 2025

Objective: This comprehensive review aims to provide an overview of the current state of Healthcare Knowledge Graphs (HKGs), including their construction, utilization models, and applications across various healthcare and biomedical research domains.

A Review on Knowledge Graphs for Healthcare: Resources, Applications, and Promises

Hejie Cui*, Jiaying Lu*, Ran Xu*, Shiyu Wang, Wenjing Ma, Yue Yu, Shaojun Yu, Xuan Kan, Chen Ling, Liang Zhao, Zhaohui S. Qin, Joyce C. Ho, Tianfan Fu, Jing Ma, Mengdi Huai, Fei Wang, Carl Yang (* equal contribution)

Journal of Biomedical Informatics (JBI) (5-Year Impact Factor: 7.7) 2025

Objective: This comprehensive review aims to provide an overview of the current state of Healthcare Knowledge Graphs (HKGs), including their construction, utilization models, and applications across various healthcare and biomedical research domains.

CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models
CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models

Wei Dai, Peilin Chen, Malinda Lu, Daniel Li, Haowen Wei, Hejie Cui, Paul Pu Liang

The International Conference on Machine Learning (ICML) 2025

Recent advances in clinical AI have enabled remarkable progress across many clinical domains. However, existing benchmarks and models are primarily limited to a small set of modalities and tasks, which hinders the development of large-scale multimodal methods that can make holistic assessments of patient health and well-being.

CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models

Wei Dai, Peilin Chen, Malinda Lu, Daniel Li, Haowen Wei, Hejie Cui, Paul Pu Liang

The International Conference on Machine Learning (ICML) 2025

Recent advances in clinical AI have enabled remarkable progress across many clinical domains. However, existing benchmarks and models are primarily limited to a small set of modalities and tasks, which hinders the development of large-scale multimodal methods that can make holistic assessments of patient health and well-being.

Multimodal Fusion of EHR in Structures and Semantics: Integrating Clinical Records and Notes with Hypergraph and LLM
Multimodal Fusion of EHR in Structures and Semantics: Integrating Clinical Records and Notes with Hypergraph and LLM

Hejie Cui, Xinyu Fang, Ran Xu, Xuan Kan, Joyce C. Ho, Carl Yang

International Medical Informatics Conference (MedInfo) 2025

Electronic Health Records (EHRs) have become increasingly popular to support clinical decision-making and healthcare in recent decades. EHRs usually contain heterogeneous information, such as structural data in tabular form and unstructured data in textual notes. Different types of information in EHRs can complement each other and provide a more complete picture of the health status of a patient.

Multimodal Fusion of EHR in Structures and Semantics: Integrating Clinical Records and Notes with Hypergraph and LLM

Hejie Cui, Xinyu Fang, Ran Xu, Xuan Kan, Joyce C. Ho, Carl Yang

International Medical Informatics Conference (MedInfo) 2025

Electronic Health Records (EHRs) have become increasingly popular to support clinical decision-making and healthcare in recent decades. EHRs usually contain heterogeneous information, such as structural data in tabular form and unstructured data in textual notes. Different types of information in EHRs can complement each other and provide a more complete picture of the health status of a patient.

Biomedical Visual Instruction Tuning with Clinician Preference Alignment
Biomedical Visual Instruction Tuning with Clinician Preference Alignment

Hejie Cui*, Lingjun Mao*, Xin Liang, Jieyu Zhang, Hui Ren, Quanzheng Li, Xiang Li, Carl Yang (* equal contribution)

The Conference on Neural Information Processing Systems (NeurIPS) 2024

Recent advancements in multimodal foundation models have showcased impressive capabilities in understanding and reasoning with visual and textual information. Adapting these foundation models trained for general usage to specialized domains like biomedicine requires large-scale domain-specific instruction datasets.

Biomedical Visual Instruction Tuning with Clinician Preference Alignment

Hejie Cui*, Lingjun Mao*, Xin Liang, Jieyu Zhang, Hui Ren, Quanzheng Li, Xiang Li, Carl Yang (* equal contribution)

The Conference on Neural Information Processing Systems (NeurIPS) 2024

Recent advancements in multimodal foundation models have showcased impressive capabilities in understanding and reasoning with visual and textual information. Adapting these foundation models trained for general usage to specialized domains like biomedicine requires large-scale domain-specific instruction datasets.

Microstructures and Accuracy of Graph Recall by Large Language Models
Microstructures and Accuracy of Graph Recall by Large Language Models

Yanbang Wang, Hejie Cui, Jon Kleinberg

The Conference on Neural Information Processing Systems (NeurIPS) 2024 IC2S2 Oral

Graphs data is crucial for many applications, and much of it exists in the relations described in textual format. As a result, being able to accurately recall and encode a graph described in earlier text is a basic yet pivotal ability that LLMs need to demonstrate if they are to perform reasoning tasks that involve graph-structured information.

Microstructures and Accuracy of Graph Recall by Large Language Models

Yanbang Wang, Hejie Cui, Jon Kleinberg

The Conference on Neural Information Processing Systems (NeurIPS) 2024 IC2S2 Oral

Graphs data is crucial for many applications, and much of it exists in the relations described in textual format. As a result, being able to accurately recall and encode a graph described in earlier text is a basic yet pivotal ability that LLMs need to demonstrate if they are to perform reasoning tasks that involve graph-structured information.

LLMs-based Few-Shot Disease Predictions using EHR: A Novel Approach Combining Predictive Agent Reasoning and Critical Agent Instruction
LLMs-based Few-Shot Disease Predictions using EHR: A Novel Approach Combining Predictive Agent Reasoning and Critical Agent Instruction

Hejie Cui, Zhuocheng Shen, Jieyu Zhang, Hui Shao, Lianhui Qin, Joyce C Ho, Carl Yang

American Medical Informatics Association (AMIA) Annual Symposium (Oral) 2024 Oral

Electronic health records (EHRs) contain valuable patient data for health-related prediction tasks, such as disease prediction. Traditional approaches rely on supervised learning methods that require large labeled datasets, which can be expensive and challenging to obtain.

LLMs-based Few-Shot Disease Predictions using EHR: A Novel Approach Combining Predictive Agent Reasoning and Critical Agent Instruction

Hejie Cui, Zhuocheng Shen, Jieyu Zhang, Hui Shao, Lianhui Qin, Joyce C Ho, Carl Yang

American Medical Informatics Association (AMIA) Annual Symposium (Oral) 2024 Oral

Electronic health records (EHRs) contain valuable patient data for health-related prediction tasks, such as disease prediction. Traditional approaches rely on supervised learning methods that require large labeled datasets, which can be expensive and challenging to obtain.

Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting
Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting

Hejie Cui*, Xinyu Fang*, Zihan Zhang, Ran Xu, Xuan Kan, Xin Liu, Manling Li, Yangqiu Song, Carl Yang (* equal contribution)

The Conference on Neural Information Processing Systems (NeurIPS) 2023

Images contain rich relational knowledge that can help machines understand the world. Existing methods on visual knowledge extraction often rely on the pre-defined format (e.g., sub-verb-obj tuples) or vocabulary (e.g., relation types), restricting the expressiveness of the extracted knowledge. In this work, we take a first exploration to a new paradigm of open visual knowledge extraction.

Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting

Hejie Cui*, Xinyu Fang*, Zihan Zhang, Ran Xu, Xuan Kan, Xin Liu, Manling Li, Yangqiu Song, Carl Yang (* equal contribution)

The Conference on Neural Information Processing Systems (NeurIPS) 2023

Images contain rich relational knowledge that can help machines understand the world. Existing methods on visual knowledge extraction often rely on the pre-defined format (e.g., sub-verb-obj tuples) or vocabulary (e.g., relation types), restricting the expressiveness of the extracted knowledge. In this work, we take a first exploration to a new paradigm of open visual knowledge extraction.

PV2TEA: Patching Visual Modality to Textual-Established Information Extraction
PV2TEA: Patching Visual Modality to Textual-Established Information Extraction

Hejie Cui, Rongmei Lin, Nasser Zalmout, Chenwei Zhang, Jingbo Shang, Carl Yang, Xian Li

Annual Meeting of the Association for Computational Linguistics (ACL-Findings) 2023

Attribute value extraction, as a fundamental task in e-Commerce services, has been extensively studied and formulated as text-based extraction. However, many attributes can benefit from image-based extraction, like the product color, shape, pattern, among others. The visual modality has long been underutilized, mainly due to multimodal annotation difficulty.

PV2TEA: Patching Visual Modality to Textual-Established Information Extraction

Hejie Cui, Rongmei Lin, Nasser Zalmout, Chenwei Zhang, Jingbo Shang, Carl Yang, Xian Li

Annual Meeting of the Association for Computational Linguistics (ACL-Findings) 2023

Attribute value extraction, as a fundamental task in e-Commerce services, has been extensively studied and formulated as text-based extraction. However, many attributes can benefit from image-based extraction, like the product color, shape, pattern, among others. The visual modality has long been underutilized, mainly due to multimodal annotation difficulty.

BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks
BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks

Hejie Cui, Wei Dai, Yanqiao Zhu, Xuan Kan, Antonio Aodong Chen Gu, Joshua Lukemire, Liang Zhan, Lifang He, Ying Guo, Carl Yang

IEEE Transactions on Medical Imaging (5-Year Impact Factor: 12.3) 2022

Mapping the connectome of the human brain using structural or functional connectivity has become one of the most pervasive paradigms for neuroimaging analysis. Recently, Graph Neural Networks (GNNs) motivated from geometric deep learning have attracted broad interest due to their established power for modeling complex networked data.

BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks

Hejie Cui, Wei Dai, Yanqiao Zhu, Xuan Kan, Antonio Aodong Chen Gu, Joshua Lukemire, Liang Zhan, Lifang He, Ying Guo, Carl Yang

IEEE Transactions on Medical Imaging (5-Year Impact Factor: 12.3) 2022

Mapping the connectome of the human brain using structural or functional connectivity has become one of the most pervasive paradigms for neuroimaging analysis. Recently, Graph Neural Networks (GNNs) motivated from geometric deep learning have attracted broad interest due to their established power for modeling complex networked data.

Brain Network Transformer
Brain Network Transformer

Xuan Kan, Wei Dai, Hejie Cui, Zilong Zhang, Ying Guo, Carl Yang

The Conference on Neural Information Processing Systems (NeurIPS) 2022 Spotlight

Human brains are commonly modeled as networks of Regions of Interest (ROIs) and their connections for the understanding of brain functions and mental disorders. Recently, Transformer-based models have been studied over different types of data, including graphs, shown to bring performance gains widely. In this work, we study Transformer-based models for brain network analysis.

Brain Network Transformer

Xuan Kan, Wei Dai, Hejie Cui, Zilong Zhang, Ying Guo, Carl Yang

The Conference on Neural Information Processing Systems (NeurIPS) 2022 Spotlight

Human brains are commonly modeled as networks of Regions of Interest (ROIs) and their connections for the understanding of brain functions and mental disorders. Recently, Transformer-based models have been studied over different types of data, including graphs, shown to bring performance gains widely. In this work, we study Transformer-based models for brain network analysis.

On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs
On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs

Hejie Cui, Zijie Lu, Pan Li, Carl Yang

The ACM International Conference on Information and Knowledge Management (CIKM) 2022 Most Influential CIKM Paper of 2022

Graph neural networks (GNNs) have been widely used in various graph-related problems such as node classification and graph classification, where the superior performance is mainly established when natural node features are available. However, it is not well understood how GNNs work without natural node features, especially regarding the various ways to construct artificial ones.

On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs

Hejie Cui, Zijie Lu, Pan Li, Carl Yang

The ACM International Conference on Information and Knowledge Management (CIKM) 2022 Most Influential CIKM Paper of 2022

Graph neural networks (GNNs) have been widely used in various graph-related problems such as node classification and graph classification, where the superior performance is mainly established when natural node features are available. However, it is not well understood how GNNs work without natural node features, especially regarding the various ways to construct artificial ones.

Interpretable GNNs for Connectome-Based Brain Disorder Analysis
Interpretable GNNs for Connectome-Based Brain Disorder Analysis

Hejie Cui, Wei Dai, Yanqiao Zhu, Xiaoxiao Li, Lifang He, Carl Yang

The International Conference on Medical Image Computing and Computer Assisted Intervention 2022 Oral

Human brains lie at the core of complex neurobiological systems, where the neurons, circuits, and subsystems interact in enigmatic ways. Understanding the structural and functional mechanisms of the brain has long been an intriguing pursuit for neuroscience research and clinical disorder therapy. Mapping the connections of the human brain as a network is one of the most pervasive paradigms in neuroscience.

Interpretable GNNs for Connectome-Based Brain Disorder Analysis

Hejie Cui, Wei Dai, Yanqiao Zhu, Xiaoxiao Li, Lifang He, Carl Yang

The International Conference on Medical Image Computing and Computer Assisted Intervention 2022 Oral

Human brains lie at the core of complex neurobiological systems, where the neurons, circuits, and subsystems interact in enigmatic ways. Understanding the structural and functional mechanisms of the brain has long been an intriguing pursuit for neuroscience research and clinical disorder therapy. Mapping the connections of the human brain as a network is one of the most pervasive paradigms in neuroscience.

How Can Graph Neural Networks Help Document Retrieval: A Case Study on CORD19 with Concept Map Generation
How Can Graph Neural Networks Help Document Retrieval: A Case Study on CORD19 with Concept Map Generation

Hejie Cui, Jiaying Lu, Yao Ge, Carl Yang

The European Conference on Information Retrieval 2022

Graph neural networks (GNNs), as a group of powerful tools for representation learning on irregular data, have manifested superiority in various downstream tasks. With unstructured texts represented as concept maps, GNNs can be exploited for tasks like document retrieval. Intrigued by how can GNNs help document retrieval, we conduct an empirical study on a large-scale multi-discipline dataset CORD-19.

How Can Graph Neural Networks Help Document Retrieval: A Case Study on CORD19 with Concept Map Generation

Hejie Cui, Jiaying Lu, Yao Ge, Carl Yang

The European Conference on Information Retrieval 2022

Graph neural networks (GNNs), as a group of powerful tools for representation learning on irregular data, have manifested superiority in various downstream tasks. With unstructured texts represented as concept maps, GNNs can be exploited for tasks like document retrieval. Intrigued by how can GNNs help document retrieval, we conduct an empirical study on a large-scale multi-discipline dataset CORD-19.

Pulmonary Vessel Segmentation based on Orthogonal Fused U-Net++ of Chest CT Images
Pulmonary Vessel Segmentation based on Orthogonal Fused U-Net++ of Chest CT Images

Hejie Cui, Xinglong Liu, Ning Huang

The International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2019

Pulmonary vessel segmentation is important for clinical diagnosis of pulmonary diseases, while is also challenging due to the complicated structure. In this work, we present an effective framework and refinement process of pulmonary vessel segmentation from chest computed tomographic (CT) images.

Pulmonary Vessel Segmentation based on Orthogonal Fused U-Net++ of Chest CT Images

Hejie Cui, Xinglong Liu, Ning Huang

The International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2019

Pulmonary vessel segmentation is important for clinical diagnosis of pulmonary diseases, while is also challenging due to the complicated structure. In this work, we present an effective framework and refinement process of pulmonary vessel segmentation from chest computed tomographic (CT) images.

All publications