Hua Shen (申华)
Tenure-Track Assistant Professor
Computer Science, NYU Shanghai
Computer Science Department, New York University
I am a tenure-track assistant professor of Computer Science at NYU Shanghai, jointly affiliated with the Computer Science Department at New York University.
I serve on NYU Shanghai's AI & Innovation Advisory Committee, where I lead the Interdisciplinary AI Research subcommittee.
I have been honored to receive four Shanghai talent awards: Pearl Elite, Pujiang, Magnolia, and Oriental.
I broadly pursue interdisciplinary research connecting AI (e.g., Natural Language Processing, Speech Processing, and Machine Learning) and Humans (e.g, Human-Computer Interaction, Computational Social Science, Psychology). Specifically, I initiated the research on Bidirectional Human-AI Alignment (NeurIPS 2025 Tutorial | CHI 2026 Workshop | NeurIPS 2025 Position Paper | ICLR & CHI 2025 Workshop | NYU Shanghai Course). My research aims to:
that enables humans to interactively explain, audit, and collaborate with agentic AI (Align Humans with AI), and integrates human feedback and values to improve agentic AI (Align AI with Humans), achieving a complete loop of Bidirectional Humans↔AI Alignment.
Concrete research directions and representative papers include:
Value Alignment:
Mind the Value-Action Gap (EMNLP 2025 Outstanding Paper);
Value Alignment Tax (ACL 2026 Findings);
Deep Value Benchmark (NeurIPS 2025);
ValueCompass (EMNLP 2025 WiNLP);
ValueFlow (Arxiv 2026)
Agentic AI Safety & Risks:
LLM Dark Patterns (CHI 2026 Best Paper Honorable Mention);
SusBench (IUI 2026)
Epistemic & Cognitive Alignment:
ConvXAI (CSCW 2023 Best Demo);
Epistemic Alignment (COLM 2025);
PromptAuditor (CHI 2025)
Behavior & Representation Alignment:
HypoCompass (AIED 2024 / IJCAI 2025 Best Paper & Best Interactive Event);
Bridging Human Interpretation and Machine Representation (CHI 2026 BiAlign)
Bidirectional Human-AI Alignment:
Bidirectional Human-AI Alignment (NeurIPS 2025 Position);
Human-AI Alignment Tutorial (NeurIPS 2025 Tutorial);
Human-AI Interaction Alignment (CHI 2026);
Bidirectional Opinion Dynamics (CHI 2026 BiAlign);
Bidirectional Alignment (ICLR 2025)
Best Paper Honorable Mention Award, (LLM Dark Pattern Paper), (Last-Author, PI), CHI 2026
Google Gemini Academic Program Award, (Single PI), Google DeepMind, 2026
Outstanding Paper Award, (Mind the Value-Action Gap Paper), (Top 1%, First-Author), EMNLP 2025
Pujiang Talent Award, (Single PI), Shanghai, China, 2025
Oriental Talent Award, (Single PI), Shanghai, China, 2025
Magnolia Talent Award, ( Single PI), Shanghai, China, 2025
Pearl Elite Talent Award, (Single PI), Shanghai, China, 2025
Best Paper, (HypoCompass Paper), (Top 1%, 1/76), AIED, 2024
Organizer, CHI 2026 BiAlign Workshop
Leading Organizer & Chair, ICLR 2025 BiAlign Workshop, CHI 2025 BiAlign SIG
Organizing Co-Chair, EMNLP 2025 WiNLP Workshop
Organizing Co-Chair, CSCW 2025 Design for Hope Workshop
Area Chair, COLM 2026
CHI 2026 Best Paper Committee, CHI 2026
Associate Chair (Poster Track), CHI 2026
Associate Chair (Main Track), CHI 2026
CHI 2026 Workshops Jury, CHI 2026
Area Chair, ACL Rolling Review 2025
Best Paper Committee, CHI 2025
Associate Chair, CHI 2025
Associate Chair, CHI 2024 LBW
I broadly pursue interdisciplinary research connecting AI (e.g., Natural Language Processing, Speech Processing, and Machine Learning) and Humans (e.g, Human-Computer Interaction, Computational Social Science, Psychology). Specifically, I initiated the research on Bidirectional Human-AI Alignment (NeurIPS 2025 Tutorial | CHI 2026 Workshop | NeurIPS 2025 Position Paper | ICLR & CHI 2025 Workshop | NYU Shanghai Course). My research aims to:
"Maximizing Capabilities AND Minimizing Risks in Human-AI Co-Evolution"
1. Minimizing Risks
2. Maximizing Capabilities
3. Dynamics & Co-evolution
I am recruiting PhD students through NYU Courant Computer Science Department. I'm also recruiting Undergraduate and Master students. See our BiAlign Lab page and welcome to reach out!
About Me
I was a Postdoctoral Scholar at the University of Washington iSchool and RAISE Center (2024-2025), and a Postdoctoral Research Fellow at University of Michigan UMSI and CSE (2023-2024). I obtained my Ph.D. degree at Penn State (2019-2023). I also interned in Google Research (now Google DeepMind) and Amazon Alexa AI (now Amazon AGI).
Deeply grateful for my mentors, collaborators, and students🧡!
Recent Activities
2026-03
Congrats to Yike for her first CHI 2026 paper, The Dark Patterns in LLMs, received Best Paper Honorable Mention Award! Welcome to share your experiences with LLM Dark Patterns in our Website!
2026-01
Received the prestigious Google Gemini Academic Program Award to support our BiAlign research with Gemini Model!
2026-01
Organizing our CHI 2026 BiAlign Workshop with our amazing collaborators!
2025-12
Truly honored to receive four talent program awards from Shanghai in 2025: Pearl Elite Talent, Pujiang Talent, Magnolia Talent, and Oriental Talent Awards. Many thanks!
2025-12
Gave an invited talk at ASRU 2025 @ Hawaii on human-centered alignment in Speech LLMs.
2025-12
Attending NeurIPS 2025 @ San Diego for one Human-AI Alignment Tutorial, and two papers: Towards Bidirectional Human-AI Alignment and Deep Value Benchmark.
2025-11
Mind the Value-Action Gap has been awarded as the Outstanding Paper Award at EMNLP 2025!
2025-11
Attending EMNLP 2025 @ Suzhou to present two papers: Mind the Value-Action Gap and ValueCompass.
Selected Honors/Awards
Selected Services
Organizer & Chair
Area Chair & Associate Chair