Invited Talks

Tutorials

Invited Talks

  • Columbia University. Oct 2025

  • University of Pennsylvania. Oct 2025

  • ICCV Workshop on Multimodal Reasoning for Agentic Intelligence. Oct 2025

  • ICCV Workshop on Multimodal Spatial Intelligence. Oct 2025

  • ICCV Workshop on Structural Priors for Vision. Oct 2025

  • ICCV Workshop on LongVid-Foundations. Oct 2025

  • RAGEN: Training Agents by Reinforcing Reasoning
    Agent AI Summit at Berkeley. Aug 2025.
    University of Edinburgh CHAI Seminar Series. Sept 2025
    Agentic AI Frontier Seminar, Sept 2025

  • See, Think, Act: Agent Training By Reinforcement Reasoning
    Cross Future AI Summit, Jul 2025

  • Why is Spatial Concept Learning Hard?
    CVPR 2025 Workshop on Visual Concepts, Jul 2025.

  • Training Agents with World Model Reasoning
    Apple Workshop on Reasoning and Planning, Jul 2025

  • LLMs for Embodied Decision Making
    ACC 2025 Workshop on LLMs in Control Design and Decision Making

  • RAGEN: Training Agents by Reinforcing Reasoning
    Google Deepmind. May 2025
    UIUC NLP Seminar. Apr 2025

  • Reasoning and Planning with Physical World
    Guest Lecture at UMich EECS 692 Advanced Artificial Intelligence. Apr 2025

  • Agent Training Under a MDP Formulation
    AAAI 2025 New Faculty Highlights. Feb 2025
    AAAI 2025 Workshop on LM4Plan. Feb 2025
    AAAI 2025 Bridge on Foundation Models and Planning. Feb 2025

  • Embodied Agent Interface: LLMs and VLMs for Embodied Reasoning and Planning
    SFU @ NeurIPS 2024. Dec 2024

  • LLMs for Embodied Agents
    EMNLP 2024 Birds of Feather. Nov 2024

  • Customizing Large Language Models to Embodied Agent interacting with Embodied Envioronments
    EMNLP 2024 CustomNLP4U Workshop. Nov 2024

  • From Large Language Models to Large Agent Models
    Keynote at Amazon-Illinois Center on AI for Interactive Conversational Experiences Fall Research Symposium 2024. Sept 2024

  • Reasoning and Planning with Physical World Knowledge
    2024 Allerton Conference on Communication, Control, and Computing. Sept 2024

  • Embodied Agent Interface: LLMs for Embodied Decision Making
    TTIC Multimodal AI Workshop 2024. Aug 2024

  • Multimodal Knowledge for Social Good
    Summer Institute in Computational Social Science 2024. Aug 2024

  • Reasoning, Planning and Compositionality in Multimodality
    SpLU-RoboNLP 2024 Workshop at ACL. Jul 2024

  • Visually Descriptive Language Modeling for Document Intelligence
    Adobe Research. Jul 2024

  • From Large Language Models to Large Agent Models
    Apple NLU Workshop 2024. Jun 2024

  • From Words to Worlds: A Close Look to Diffusion Models (through an NLP Lens)
    UIUC NLP Seminar. Jun 2024

  • The Missing Knowledge in LLMs to Interact with the Physical World
    Midwest Machine Learning Symposium 2024. May 2024

  • Beyond the Beaten Path: Exploring the Role of Graphs in Multimodal Foundation Models
    Keynote Talk at NeurIPS 2023 Workshop on New Frontiers in Graph Learning. Dec 2023

  • LLMs for robotics: Modeling the Knowledge of the Physical World
    Stanford Vision and Learning Seminar. Oct 2023

  • Knowledge Foundation Models
    Adobe Research. Oct 2023

  • Modeling the Semantics of the Physical World
    Stanford CogAI. Jun 2023

  • Towards Factuality in Information Access: Multimodal Knowledge Acqusition and Reasoning [Slides]
    Carnegie Mellon University, LTI. Feb 2023
    Northwestern University, CS. Feb 2023
    Northeastern University, ECE. Feb 2023
    Purdue University, CS. Feb 2023
    Rice University, CS. Feb 2023
    Virginia Tech, CS. Feb 2023
    Max Planck Institute. Feb 2023
    UVA, CS. Mar 2023
    MBZUAI. Mar 2023
    U Washington St Louis, CS. Mar 2023
    University of Toronto, CS+ECE. Mar 2023
    UC San Diego, ECE. Feb 2023
    UC Davis, CS. Mar 2023
    UC Los Angeles, ECE. Apr 2023

  • From Entity-Centric to Event-Centric Multimodal Event Knowledge Acquisition
    EE CS Rising Star, University of Texas at Austin, USA. Oct 2022.

  • Towards Accurate Intelligent Analysis: Event-Centric Multimedia Knowledge Extraction
    DARPA Forward (Invite-Only), USA. Oct 2022.

  • Event-Centric Multimedia Data Understanding
    Ohio State University, USA. Oct 2022.
    Singapore Management University, Singapore. Oct 2022.
    George Mason University, USA. Oct 2022.
    North Carolina State University, USA. Oct 2022.

  • Multimedia Event Extraction: From Object-Centric to Event-Centric
    Virginia Tech, USA. Sept 2022.

  • Event Knowledge Graph Construction
    LOGS Graph Reasoning Seminar. Aug 2022.

  • Event Graph Structures in Vision-Language Understanding
    DataFun. Jun 2022.

  • Connecting Vision and Text using Event Structures
    NewsBreak. Apr 2022.

  • Memories as Repositories of Events: Structural Event Knowledge Acquisition
    University of Notre Dame. Feb 2022.

  • Comprehensive Event Understanding in Multimedia Data
    USC ISI. Dec 2021.

  • Structural Event Knowledge Acquisition from Multimedia Data
    UIUC NLP Seminar. Nov 2021.

  • Event Extraction and Reasoning in Multimedia News Data
    Microsoft Research. Nov 2021.

  • Improving Visual Event and Argument Role Understanding with Contrastive Image-Language Pretraining
    Microsoft Research. Aug 2021.

  • Fine-Grained Knowledge Extraction System from Multimedia Data
    ai.science. Oct 2020.

  • Event Understanding and Narration for Multimedia Data
    Intel MDI Research Lab. May 2020.