BiAlign Lab Logo
👏 Welcome to our BiAlign Lab!
BiAlign Lab - explores the dynamic interaction and adaptation between humans and AI, with a focus on bidirectional human-AI alignment. Our research bridges AI/ML, HCI, and social computing to design systems that are not only intelligent, but also responsive to human values and societal needs.
We work closely with academic and industry partners worldwide, through efforts like the BiAlign Workshop, position paper, and ongoing collaborations, all contributing to more trustworthy and responsible AI.
Lab News
  • 2025-09 Hua is teaching a new course: Bidirectional Human-AI Alignment @NYU Shanghai.
  • 2025-08 We will give a Human-AI Alignment Tutorial @NeurIPS 2025.
  • 2025-08 Mind the Value-Action Gap paper accepted @EMNLP 2025 Main.
  • 2025-08 Hua gave a talk on Bidirectional & Value Alignment @UC Berkeley Agentic AI Summit
  • 2025-08 Epistemic Alignment paper accepted @COLM 2025.
  • 2025-04 Our ICLR 2025 Workshop on Bidirectional Human-AI Alignment was successfully held.
  • 2025-04 Our CHI 2025 SIG on Bidirectional Human-AI Alignment was successfully held.
  • 2025-04 We released our Position Paper with Systematic Review on Bidirectional Human-AI Alignment.
  • Contact Us

    Thank you for your interest in our research! We are always welcome passionate and self-motivated researchers to join our team!
  • Our lab students will be NYU students of either Courant CS or Tandon CSE Programs.
  • We are open to work remotely from anywhere on the earth.
  • You might be co-advised by me and my core collaborators in academia or industry.
  • Prospective PhDs
    We have several PhD openings, and are looking for self-motivated PhD students joining in 2026!
  • PhD Program: You can apply for either NYU Courant Institute of Mathematical Sciences or NYU Tandon School of Engineering, and express your interest in being associated with NYU Shanghai. The final admission decision is made by the NYU committee. For more details regarding the program, please visit the NYU Shanghai Computer Science Ph.D. Program link.
  • Flexibility in Locations and Future Careers (US or China): You will spend Year 1 at NYU New York Campus to finish PhD courses. Starting from Year 2, you can choose your location working with me in Shanghai, New York, or remotely. For non-US citizens, students are eligible for F1 OPT after graduation, offering opportunities to work in the US.
  • Competitive Stipends: The stipends offered to PhD students are competitive. I am happy to share more in our 1:1 meetings.
  • Undergraduate & Master Students
  • We always welcome undergraduate and graduate studnets from diverse background! Visiting roles can be either in-person or remote. If you are intersted in joining us as an master, undergraduate, or pre-doc researcher, please send me an email with your CV.
  • Prospective Postdocs
  • I am not actively recruiting postdocs at the moment. However, I’m open to exploring 0–1 potential postdoc opportunities for strong candidates! If you are intersted, please send me an email with your CV.
  • Visitors & Collaborators
  • We generally prefer visitors to stay for at least 6 months for high-quality work. If you are interested in visiting our research lab, please send me an email with details.
  • Mentored Students

    I’ve had the privilege of working with many outstanding PhD, Master’s, and undergraduate students during my PhD and Postdoc time. They should be able to offer a fair perspective on the pros and cons with me as a mentor! But please be mindful and respect their time if you decided to contact them. Thanks 🧡!
    Student Name

    Christina Ma (PhD)

    CMU

    Research: Human-LLM Collaboration

    Papers: HypoCompass [AIES'24], ROPE [TOCHI'25]

    Student Name

    Nick Clark (PhD)

    UW

    Research: Humans-LLM Epistemic Alignment

    Papers: ValueCompass, Epistemic Alignment

    Student Name

    Navreet Kaur (PhD)

    UW

    Research: NLP, Responsible AI and Governance

    Papers: Ongoing

    Student Name

    Marisa Yang (PhD)

    UIUC

    Research: AI Privacy Risks and Values

    Papers: ValueCompass

    Student Name

    Snehal Prabhudesai (PhD)

    UMich

    Research: LLM Auditing and Policies

    Papers: PromptAuditor [CHI'25]

    Student Name

    Anindya Das Antar (PhD)

    UMich

    Research: LLM Auditing and Policies

    Papers: PromptAuditor [CHI'25]

    Student Name

    Tuc Nguyen (PhD)

    Indiana University

    Research: LLM Explanation Algorithms and Human Eval

    Papers: NoMatterXAI [AAAI'25]

    Student Name

    Kenan Alkiek (PhD)

    UMich

    Research: LLM Explanation and Reasoning

    Papers: BiAlign Survey

    Student Name

    Jooyoung Lee (PhD)

    Penn State -> Amazon AGI

    Research: LLM-Generated DeepFake Detection

    Papers: Identify DeepFake [HCOMP'23]

    Student Name

    Gillian Soekawan (Master)

    UW

    Research: Human-AI Interaction and Values

    Papers: Ongoing

    Student Name

    Weirui Peng (Master)

    Columbia -> UMich PhD

    Research: Human-LLM Collaboration

    Papers: ROPE [TOCHI'25]

    Student Name

    Anmol Mansingh (Master)

    UMich

    Research: LLM Auditing and Conversation Analysis

    Papers: PromptAuditor [CHI'25]

    Student Name

    Ananya Kasi (Undergrad)

    UMich -> Georgia Tech PhD

    Research: LLM Auditing

    Papers: PromptAuditor [CHI'25]

    Student Name

    Reuben Lee (Undergrad)

    Penn State -> Capital One

    Research: Human-AI Interactive Systems

    Papers: ConvXAI [CSCW'23]

    Student Name

    Sushirita Rakshit (Undergrad)

    UMich

    Research: human-centered LLM and Reasoning

    Papers: BiAlign Survey