Publications

(2026). Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs. NeurIPS 2026.

arXiv

(2026). SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation. NeurIPS 2026.

arXiv

(2026). StaRPO: Stability-Augmented Reinforcement Policy Optimization. NeurIPS 2026.

arXiv

(2026). PADFormer: Pose-Agnostic Anomaly Detection from Sparse View Images. ECCV 2026.

Springer arXiv

(2026). Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning. ACL 2026 Findings.

ACL Anthology arXiv

(2026). On-Policy Self-Distillation for Efficient Diffusion Language Models with Early-Stage Calibration. ACL 2026 Findings.

ACL Anthology

(2026). Exploring Collaboration Breakdowns Between Provider Teams and Patients in Post-Surgery Care. CHI 2026.

ACM DL arXiv

(2026). LLM-based Embodied Conversational Agent for Reducing Foreign Language Speaking Anxiety in Social VR. CHI 2026.

ACM DL

(2026). OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation. ACL 2026.

ACL Anthology arXiv

(2026). Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents. ACL 2026.

ACL Anthology arXiv

(2026). Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning. ICLR 2026.

OpenReview arXiv

(2026). SFT Doesn’t Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs. ICLR 2026.

OpenReview

(2026). RECOVER: Designing a Large Language Model-based Remote Patient Monitoring System for Postoperative GI Cancer Care. CSCW 2026.

Source Document ACM DL arXiv Project

(2026). MIND: Empowering Mental Health Clinicians with Multimodal Data Insights through a Narrative Dashboard. CHI 2026.

ACM DL arXiv

(2026). Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight. CHI 2026.

ACM DL arXiv

(2026). Agent A/B: Automated and Scalable A/B Testing on Live Websites with Interactive LLM Agents. CHI EA 2026.

ACM DL

(2026). WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch. ACM HEALTH 2026.

ACM DL arXiv

(2026). SurgWound-Bench: A Benchmark for Surgical Wound Diagnosis. npj Digit. Med. 2026.

Nature arXiv

(2026). Harness updating is not harness benefit: Disentangling evolution capabilities in self-evolving llm agents. EMNLP 2026.

ACL Anthology arXiv

(2026). “Should I Give Up Now?” Investigating LLM Pitfalls in Software Engineering. TOSEM 2026.

ACM DL arXiv

(2026). Evo-harness: Context-to-harness skill compilation for self-evolving agents. EMNLP 2026.

ACL Anthology arXiv

(2026). The Obvious Invisible Threat: Vulnerabilities of LLM-Powered GUI Agents to Adversarial UI Manipulations in Web Interaction Tasks. ACM TAISAP 2026.

(2026). Toward Metaphor-Fluid Conversation Design for Voice User Interfaces. CUI 2026.

ACM DL arXiv

(2025). Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction. EMNLP 2025 Findings.

ACL Anthology arXiv

(2025). Promoting Prosociality via Micro-acts of Joy: A Large-Scale Well-Being Intervention Study. CHI 2025.

ACM DL

(2025). UXAgent: An LLM Agent-Based Usability Testing Framework for Web Design. CHI EA 2025.

ACM DL arXiv

(2025). DoctorPupil: A Virtual Reality System for Parkinson’s Diagnosis through Task-Evoked Pupil Response. IEEE JBHI.

IEEE Xplore

(2024). Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults. IMWUT 2024.

ACM DL

(2024). Mental-LLM: Leveraging large language models for mental health prediction via online text data. IMWUT 2024.

ACM DL arXiv

(2024). Rethinking Human-AI Collaboration in Complex Medical Decision Making: A Case Study in Sepsis Diagnosis. CHI 2024.

ACM DL arXiv Project

(2024). SepsisLab: Early Sepsis Prediction with Uncertainty Quantification and Active Sensing. KDD 2024.

ACM DL

(2024). Building LLM-based AI Agents in Social Virtual Reality. CHI EA 2024.

ACM DL

(2024). Evaluating the LLM Agents for Simulating Humanoid Behavior. CHI 2024.

(2024). Challenges and Opportunities of LLM-Based Synthetic Personae and Data in HCI. CSCW 2024.

ACM DL

(2024). Talk2Care: Facilitating Asynchronous Patient-Provider Communication with Large-Language-Model. AAAI Symposium 2024.

AAAI arXiv

(2023). Beyond Labels: Empowering Human with Natural Language Explanations through a Novel Active-Learning Architecture. EMNLP 2023 Findings.

ACL Anthology

(2023). Are Fairy Tales Fair? Analyzing Gender Bias in Temporal Narrative Event Chains of Children’s Fairy Tales. ACL 2023.

ACL Anthology

(2023). Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Design. CHI 2023.

ACM DL arXiv

(2023). Exploring the Use of Personalized AI for Identifying Misinformation on Social Media. CHI 2023.

ACM DL

(2023). PaniniQA: Enhancing Patient Education Through Interactive Question Answering. TACL 2023.

MIT Press arXiv

(2023). SHAI 2023: Workshop on Designing for Safety in Human-AI Interactions. IUI 2023.

ACM DL

(2023). Human-Centered Design and Evaluation of AI-Empowered Clinical Decision Support Systems: A Systematic Review. Frontiers CS.

Frontiers

(2023). Deep Learning–Assisted Gait Parameter Assessment for Neurodegenerative Diseases: Model Development and Validation. JMIR.

JMIR

(2022). MBTI Personality Prediction for Fictional Characters Using Movie Scripts. EMNLP 2022 Findings.

ACL Anthology arXiv

(2022). Towards a Progression-Aware Autonomous Dialogue Agent. NAACL 2022.

ACL Anthology arXiv

(2022). A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Prediction. NAACL 2022.

ACL Anthology

(2022). StoryBuddy: A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement. CHI 2022.

ACM DL arXiv

(2022). Fantastic Questions and Where to Find Them: FairytaleQA–An Authentic Dataset for Narrative Comprehension. ACL 2022.

ACL Anthology

(2022). Documentation Matters: Human-Centered AI System to Assist Data Science Code Documentation in Computational Notebooks. TOCHI 2022.

ACM DL arXiv

(2022). Semantic Feature Discovery with Code Mining and Semantic Type Detection. AAAI 2022.

AAAI

(2022). Gemv2: Multilingual nlg benchmarking in a single line of code. EMNLP 2022.

ACL Anthology arXiv

(2022). Human–computer integration: Towards integrating the human body with the computational machine. FnT HCI.

Now Publishers

(2022). Label Sleuth: From unlabeled text to a classifier in a few hours. EMNLP 2022.

ACL Anthology arXiv

(2022). GeoDeepShovel: A platform for building scientific database from geoscience literature with AI assistance. Geosci. Data J..

Wiley

(2022). DeepBrain: Enabling Fine-Grained Brain-Robot Interaction through Human-Centered Learning of Coarse EEG Signals from Low-Cost Devices. IMWUT.

ACM DL

(2021). D2S: Document-to-Slide Generation Via Query-Based Text Summarization. NAACL 2021.

ACL Anthology

(2021). CASS: Towards building a social-support chatbot for online health community. CSCW 2021.

ACM DL arXiv

(2021). “Brilliant AI doctor” in rural clinics: Challenges in AI-powered clinical decision support system deployment. CHI 2021.

ACM DL arXiv

(2021). How ai developers overcome communication challenges in a multidisciplinary team: A case study. CSCW 2021.

ACM DL

(2021). Model lineupper: Supporting interactive model comparison at multiple levels for automl. IUI 2021.

ACM DL arXiv

(2021). AutoDS: Towards human-centered automation of data science. CHI 2021.

ACM DL arXiv

(2021). Graph-Augmented Code Summarization in Computational Notebooks. IJCAI 2021.

IJCAI

(2021). Automated data science for relational data. ICDE 2021.

IEEE Xplore

(2021). Data-debugging through interactive visual explanations. PAKDD Workshop 2021.

Springer

(2021). What makes a well-documented notebook? a case study of data scientists’ documentation practices in kaggle. CHI EA 2021.

ACM DL

(2021). Designing ai to work with or for people?. CHI EA 2021.

ACM DL

(2021). Autotext: An end-to-end autoai framework for text. AAAI 2021.

AAAI

(2021). Effect of ai explanations on human perceptions of patient-facing ai-powered healthcare systems. J. Med. Syst. 2021.

Springer

(2021). Utilization of self-diagnosis health chatbots in real-world settings: case study. JMIR 2021.

JMIR

(2021). Patients’ perceptions of using artificial intelligence (AI)-based technology to comprehend radiology imaging data. Health Inform. J..

SAGE

(2021). Towards A Diverse, Inclusive, Accessible and Equitable AAAI International Conference on Web and Social Media (ICWSM). ICWSM 2021.

(2021). How Data Scientists Improve Generated Code Documentation in Jupyter Notebooks.. IUI Workshop.

(2020). Exploring Information Needs for Establishing Trust in Automated Data Science Systems. IUI 2020.

(2020). AutoAIViz: opening the blackbox of automated artificial intelligence with conditional parallel coordinates. IUI 2020.

ACM DL

(2020). Next steps for human-computer integration. CHI 2020.

ACM DL

(2020). An ADMM based framework for automl pipeline configuration. AAAI 2020.

AAAI arXiv

(2020). Trust in AutoML: exploring information needs for establishing trust in automated machine learning systems. IUI 2020.

ACM DL arXiv

(2020). From human-human collaboration to Human-AI collaboration: Designing AI systems that can work together with people. CHI EA 2020.

ACM DL

(2020). AutoAI: Automating the end-to-end ai lifecycle with humans-in-the-loop. IUI 2020.

ACM DL

(2020). Chinese CHI 2020 Workshop. CHI EA 2020.

ACM DL

(2020). Lay individuals’ perceptions of artificial intelligence (AI)-empowered healthcare systems. ASIS&T 2020.

Wiley

(2020). IBM AutoAI: Human-in-the-Loop Automated Machine Learning Supports Data Scientists to Build Better Models.. KDD Workshop.

(2019). How data scientists work together with domain experts in scientific collaborations: To find the right answer or to ask the right question?. CSCW 2019.

ACM DL

(2019). Context-aware conversation thread detection in multi-party chat. EMNLP 2019.

ACL Anthology

(2019). Out-of-domain detection for low-resource text classification tasks. EMNLP 2019.

ACL Anthology

(2019). What can gestures tell? Detecting motor impairment in early Parkinson’s from common touch gestural interactions. CHI 2019.

ACM DL

(2019). Extracting multiple-relations in one-pass with pre-trained transformers. ACL 2019.

ACL Anthology arXiv

(2019). How data science workers work with data: Discovery, capture, curation, design, creation. CHI 2019.

ACM DL

(2019). Conversational agents: Acting on the wave of research and development. CHI EA 2019.

ACM DL

(2019). HCI in China: Research Agenda, Education Curriculum, Industry Partnership, and Communities Building. CHI EA 2019.

ACM DL

(2019). Human-ai collaboration in data science: Exploring data scientists’ perceptions of automated ai. PACM HCI.

ACM DL

(2018). Face Value? Exploring the effects of embodiment for a group facilitation agent. CHI 2018.

ACM DL

(2018). All Work and No Play? Conversations with a Question-and-Answer Chatbot in the Wild. CHI 2018.

ACM DL

(2018). Implicit detection of motor impairment in Parkinson’s disease from everyday smartphone interactions. CHI EA 2018.

ACM DL

(2018). Writing together: Online synchronous collaboration in middle school. JAAL.

Wiley

(2016). Answerer engagement in an enterprise social question & answering system. iConference 2016.

IDEALS

(2015). DocuViz: visualizing collaborative writing. CHI 2015.

ACM DL

(2015). How students collaboratively write using google docs. iConference 2015.