Talks

Selected Invited Talks

• Stabilizing and Scaling Agentic RL with Budget-Aware Control
  Google, 2026
• CuraBench: A Benchmark Dataset Generation System for Healthcare AI Evaluation
  RAISE Health Symposium, Stanford Medicine, 2025
• Empowering Medical LLMs: Holistic Evaluation and Clinician-Guided Instruction Tuning
  UChicago/TTIC NLP Seminar, February 27, 2025
• Towards Trustworthy Foundation Model Adaptation and Evaluation for Healthcare
  University of Michigan AI Symposium, October 2024
• Biomedical Visual Instruction Tuning with Clinician Preference Alignment
  The University of British Columbia, October 2024
• Advancing Healthcare with Multimodal Structural Knowledge
  UCLA; Stanford University; Massachusetts General Hospital, Harvard Medical School; Zhejiang University; Shanghai Jiao Tong University; Fudan University; Tongji University; Peking University, 2023-2024
• Expanding the Frontiers of LLM Tuning: Instruction Tuning Across Modalities and Time
  Amazon, 2024
• Advance Healthcare with Multimodal Structured Knowledge
  EECS Rising Star Workshop, Georgia Tech, 2023
• PTGB: Pre-Train Graph Neural Networks for Brain Network Analysis
  June 23, 2023
• PV2TEA: Patching Visual Modality to Textual-Established Information Extraction
  KnowledgeNLP-KDD 2023 Workshop
• BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks
  University of Rochester, April 2021
• Effective and Interpretable Graph Neural Networks for Graphs Constructed from Multimodality Data
  Microsoft Search, Assistant and Intelligence, April 2021