Organizers

Core Organizers

Photo

Biography

Colin Lin, (Leader) Master’s student in Electrical and Computer Engineering at Carnegie Mellon University, Bachelor of Science in Computer Science from Rensselaer Polytechnic Institute. Leading project: Evaluation and Benchmarking Suite for Financial LLMs and Agents. Lead organizer of the Open FinLLM Leaderboard initiative, driving the integration of regulatory reporting benchmarks including CDM, MOF and XBRL frameworks. Author of “Analyzing Cascading Outbreak of GameStop Event: A Practical Approach Using Network Analysis and Large Language Models” presented at ICAIF 2024. Contributor to AI4Finance open-source ecosystem with focus on reinforcement learning applications in financial LLM development.

	Kaiwen He holds a B.S. in Computer Science from Rensselaer Polytechnic Institute. Core developer of the project Evaluation and Benchmarking Suite for Financial LLMs and Agents. His primary responsibilities include developing and maintaining the evaluation pipeline, executing large-scale assessments, and producing the final rankings for participating teams. Organizer of SecureFinAI Contest 2025; Co-author of Regulations Challenge at COLING 2025 report paper; Technical Program Committee of Secure Financial Intelligence with Open Models.
	Qingchuan Zhang, B.S. Computer Science student at Rensselaer Polytechnic Institute (RPI). Contributes to the Evaluation and Benchmarking Suite for Financial LLMs and Agents, and supports the Open FinLLM Leaderboard with evaluation pipeline development and benchmarking maintenance. Focused on building a FinGPT-style sentiment benchmark for systematic model assessment. Contributed to the NeurIPS LLM Evaluation Workshop work on financial LLM evaluation and to the FinTagging project, helping evaluate LLMs on structured financial information extraction and XBRL tagging tasks.
	Yupeng Cao, current Ph.D. candidate in the Electrical and Computer Engineering Department at Stevens Institute of Technology. His research interests include Natural Language Processing (NLP), Multimodal, Trustworthy AI, and their application in the financial domain. He has several publications about multimodal, LLMs, and multi-agent in financial domains, including FinNLP workshop, ICAIF, ACL, and NeurIPS. He served as a PC member for the 9th FinNLP workshop and Session Chair @ACM ICAIF’24. He organized the Agent-Based Single Cryptocurrency Trading Challenge @COLING 2025. He also hosted the “TechFin” social event at NeurIPS 2024, with 100+ participants.
	Junshuo Liu, (Task 2)(M.S., Columbia University; B.S., Stony Brook University) is a Research Assistant at the SecureFinAI Lab and a contributor to the FinAI Contest 2026 at IEEE IDS on Reliable Agentic FinSearch. His research focuses on evaluating the proficiency of financial agents in numerical and temporal reasoning. His interests include Machine Learning, Computerized Adaptive Testing (CAT), and agent benchmarking in the financial domain.
	Tianlei Zhu, (Task 2) Research Assistant at Columbia University’s SecureFinAI Lab and holds a Master’s degree from Columbia University. His current work contributes to the FinRL Contest 2026 through Agentic FinSearch, focusing on hallucination patterns and reliability in financial information retrieval. His research interests include LLM evaluation and benchmarking for financial NLP (e.g., hallucination and sentiment/emotion analysis), multilingual financial misinformation detection, and trustworthy AI. Previously, he collaborated on computer vision research with collaborators at HKU and NUS.
	Felix Tian, (Task 2) Currently pursuring a bachelor of science in Information Technology & Web Science at Rensselaer Polytechnic Institute. He is the lead developer of the FinGPT search agent, a search agent powered by the FinGPT model. He has worked on the full stack development of the FinGPT search agent for two years. He is the first author of the paper “Customized FinGPT Search Agent Using Foundational Models” published at ACM ICAIF 2024. He has also contributed to the Open Financial LLM Leaderboard project. Aside from his technical background, Felix also has expertise in UX, web design and graphic design.
	Hanlin Ding, (Task 3) undergraduate at Rensselaer Polytechnic Institute. Interested in financial sentiment analysis, prediction market arbitrage, and reinforcement learning for decision-making in market settings. He contributed to the Evaluation and Benchmarking Suite for Financial LLMs and Agents by designing and refining benchmark question sets to evaluate LLM performance on financial sentiment tasks.
	Chenri Luo, focuses on developing and benchmarking financial AI agents and large language models for reliable decision support. He holds a Master’s degree in Applied Analytics from Columbia University and a Bachelor’s in Business Economics with a Data Science minor from UC San Diego. Chenri’s work spans financial document intelligence (SEC filings and XBRL), model evaluation and error taxonomy for finance reasoning, and scalable pipelines for model fine-tuning and deployment. His prior experience includes internships in financial analytics, investment research, and risk modeling, enabling him to connect technical innovation with real-world financial workflows. He is passionate about open-source community building and aims to make this contest a high-quality benchmark for next-generation finance AI systems.
	Chunlin Feng, (Task 3) undergraduate student at Rensselaer Polytechnic Institute. His research interests lie in reinforcement learning and its applications in finance, with a focus on developing standardized market environments. He is the project lead of Standardized Market Environments for Financial Reinforcement Learning, which was presented at the NeurIPS 2025 Workshop on Generative AI in Finance.
	Jinbo. Majoring in Mathematics, Computer Science, and Economics at Rensselaer Polytechnic Institute. Leading a project on AI tutor agents for foundational mathematics and computer science education. Co-author of “XBRL-Agent: Leveraging Large Language Models for Financial Report Analysis” at ICAIF 2024. Currently focusing on reasoning-model-based agents for mathematics and finance.
	Jingyu Huang, undergraduate at the University of Wisconsin–Madison. Interested in financial LLM applications, retrieval-augmented generation, and decision-making systems for regulatory and investment-related settings. He contributed to finance-focused LLM evaluation and systems development by building an EMIR-specific RAG QA agent and designing investment- and regulation-oriented task suites to assess model performance on financial reasoning and compliance queries.
	Rick Chen (Task 4: VC Bench) Master’s student in Mathematics at University of Oxford. Project Lead of VC Bench: Benchmarking LLMs in Venture Capital. Completed research under Vela Research, looking at LLM-powered decision making systems, as well as anonymization and standardization techniques for venture capital datasets.
	Ben Griffin (Task 4: VC Bench) PhD student in Machine Learning and Neuroimaging at the University of Oxford. Research focuses on large-scale predictive modelling with an emphasis on interpretability and biomarker discovery. Core contributor to the think-reason-learn framework at Vela Research (Vela Partners), including the development of the Random Rule Forest method for startup success prediction, which helped inspire VCBench.
	Aaron Ontoyin Yin (Task 4: VC Bench) focusing on deep learning, robotics, and explainable AI. He is also a co-author of VCBench, a benchmark for LLMs in venture capital. Aaron is a core contributor to the GPTree and GPT-HTree frameworks, which leverage LLM-powered decision trees. Aaron holds a degree from the University of Mines and Technology (UMaT), Ghana.
	Kelvin Amoaba (Task 4: VC Bench) Software Engineer at Vela Research, specializing in building scalable systems and exploring low-level architecture, cloud computing, and software infrastructure. Kelvin is a contributor to VCBench and has conducted research on LLM-powered feature engineering for rare-event prediction. He is also the creator of projects such as Logdeck, a Docker monitoring platform, and is-temp.com, a temporary email service. Kelvin is an alumnus of the University of Mines and Technology (UMaT), Ghana.
	Zakari Salifu (Task 4: VC Bench) Software Engineer at Vela Research, with expertise in LLM-powered segmentation, feature engineering, and automated labeling for venture capital. Zakari is a co-author of VCBench and a paper on founder assessment using LLM-powered techniques. His work focuses on predicting rare, high-impact outcomes in venture capital through advanced AI methodologies. He is an alumnus of the University of Cape Coast, Ghana.
	Yigit Ilhamur (Task 4: VC Bench), Co-founder and General Partner at Vela Partners, an AI-native venture capital firm that has supported over 40 AI startups since 2017. He holds an MSc in Computer Science from the University of Oxford (2018). Prior to co-founding Vela Partners, Yigit was a Product Manager at Google Cloud in Mountain View. He is an entrepreneur, engineer, and investor, and a co-author of several research papers including VCBench, GPTree, and LLM-AR, focusing on LLM-powered decision-making and AGI for venture capital.
	Mostapha Benhenda (Task 4: VC Bench) PhD, Sorbonne Paris North University. Core team member of AI4Finance Foundation. Developed FinRL-DeepSeek, a computational finance and automated trading project combining reinforcement learning and large language models. Now interested in applying LLM-based quantitative finance methods to venture capital, and introduced the VC Bench task to the SecureFinAI Contest 2026.

Advisors

Photo	Biography
	Keyi Wang, (Leader) Master’s at Northwestern University, Bachelor’s at Columbia University. Organizer of FinAI Contest 2025 at IEEE CSCloud, FinRL Contest 2025 at IEEE IDS, FinRL Contest 2024 and FinRL Contest 2023 at ACM ICAIF conferences, and Regulations Challenge at COLING 2025. Reviewer of ACM ICAIF conferences. Interested in machine learning and financial engineering.
	Jiechao Gao, Jiechao is currently a Postdoctoral Research Scientist at Stanford University. His research interests include machine learning, large-scale foundation models, interpretability, reinforcement learning, federated learning algorithms, and applications in distributed networks, cyber-physical systems, cloud computing, and financial environments. He has served as an Area Chair, Program Committee, and reviewer for leading conferences and journals such as NeurIPS, ICML, ICLR, KDD, AAAI, IJCAI, IEEE TNNLS, IEEE IoT Journal, etc. He has also actively contributed to community building, serving as Organizer of FinAI Contest 2025 at IEEE CSCloud, FinRL Contest 2025 at IEEE IDS, and FinRL Contests 2023–2024 at ACM ICAIF. In 2024 and 2025, he was recognized in the Stanford Elsevier Top 2% Scientist list.
	Xiao-Yang Liu. His research interests include deep reinforcement learning, financial applications, and quantum computing. He created several open-source projects, such as FinRL and FinGPT. He contributed chapters to a textbook on reinforcement learning for cyber-physical systems and a textbook on tensors for data processing. He serves as a PC member for NeurIPS, ICML, ICLR, AAAI, IJCAI, AISTATS, and ICAIF. He also served as a Session Chair for IJCAI 2019. He organized Financial Challenges in Large Language Models (FinLLM)@IJCAI 2024, FinRL Competition at ACM ICAIF 2023, the First/Second Workshop on Quantum Tensor Networks in Machine Learning (QTNML) at NeurIPS 2020/2021, IJCAI 2020 Workshop on Tensor Networks Representations in Machine Learning, and the NeurIPS 2019 Workshop on Machine Learning for Autonomous Driving.