Talks & Services
     Talks 
    
        NYU Shanghai, 2025.9 & 2025.10, Towards Bidirectional Human-AI Alignment   
        AI & Philosophy Workshop @ Fudan & Hong Kong University, 2025.9, The Two-Way Street of Alignment   
        UC Berkeley, 2025.8, Towards Bidirectional Human-AI Alignment   
        Uniphore, 2025.8, Towards Bidirectional Human-AI Alignment   
        University of Washington, 2025.4, Towards Bidirectional Human-AI Alignment   
        New York University, 2025.2, Towards Bidirectional Human-AI Alignment   
        Penn State University, 2025.2, Towards Bidirectional Human-AI Alignment   
        Amazon AGI, 2025.2, Towards Human-Centered Alignment in Speech Language Models   
        University of Texas, Austin, 2025.1, Towards Bidirectional Human-AI Alignment   
        Northeastern University, 2024.11, Towards Bidirectional Human-AI Alignment via Interaction   
        Cornell University, 2024.11, Towards Bidirectional Human-AI Alignment via Interaction   
        Columbia University, 2024.11, Towards Bidirectional Human-AI Alignment via Interaction   
        University of Washington, 2024.11 & 2024.10, Towards Bidirectional Human-AI Alignment via Interaction        
        Google DeepMind, 2024.10, Towards Human-Centered Alignment in Speech Language Models        
        Virginia Tech, 2024.10, Towards Bidirectional Human-AI Alignment via Interaction
        Microsoft, Responsible & Open AI Research, 2024.7, Towards Bidirectional Human-AI Alignment via Interaction        
        University of Illinois Urbana-Champaign, 2024.7, Towards Bidirectional Human-AI Alignment via Interaction
        EMNLP'23, 2023.12, MultiTurnCleanup: A Benchmark for Multi-Turn Spoken Conversational Transcript Cleanup
        University of Michigan, 2023.10 & 2023.11, Towards Human-Centered AI Alignment via Interaction
        Rising Star of Data Science, 2023.11, Towards Useful AI Interpretability via Interactive AI Explanations [Slide][Poster]
        Carnegie Mellon University, 2023.07, Towards Useful AI Interpretability via Interactive AI Explanations
        Princeton University, 2023.05, Towards Useful AI Interpretability via Interactive AI Explanations
        CHI'23 In2Writing Workshop, 2023.04, Parachute: Evaluating Interactive Human-LM Co-writing Systems
        IUI'23, 2023.03, ScatterShot: Interactive In-context Example Curation for Text Transformation 
        Google Research, 2023.01, A Benchmark for Multi-Turn Spoken Conversational Transcript Cleanup
        University of Notre Dame, 2022.09, Useful XAI via Interactive AI Explanations 
        Amazon Science, 2022.08, Auto-Regressive Language Model Distillation 
        Amazon Science, 2021.08, Improving Fairness in Speaker Verification Models 
        CHI'21 HCXAI Workshop, 2021.05, A Review on Human-Centered Explainable NLP