Joseph Kim

Joseph Kim Email: joseph_kim@csail.mit.edu

Bio

**I am now an AI Scientist at Invitae, the largest and fastest genetic testing company in the world!**
Updates to the website coming soon..

I was a Ph.D. candidate in the Computer Science and Artificial Intelligence Laboratory (CSAIL) at Massachusetts Institute of Technology. I was a member of the MIT Interactive Robotics Group, advised by Prof. Julie Shah.

My Ph.D. research was in the field of Human-AI Collaboration, with focus on providing decision support for human-agent teams. My thesis investigated the design of AI agents that can interact naturally with multiple human decision-makers to help them reach agreement and generate high-quality plans prior to execution. I infuse computational models from machine learning (e.g., reinforcement learning, Bayesian networks) and symbolic reasoning (e.g., automated planning, temporal logics) with insights from human factors to develop novel algorithms and systems that empower human decision-making.

I received my M.S. in Aeronautics & Astronautics from MIT and my B.S. in Aerospace Engineering from University of Illinois at Urbana-Champaign. I have work experiences from IBM Research AI, MIT Lincoln Laboratory, and Northrop Grumman Aerospace Systems. I also was a NSF Graduate Research Fellow.

Research

Publications

Teaching

News

Oct '19   I successfully passed my thesis defense and completed my Ph.D. dissertation! You can read my Ph.D. dissertation here and check out the defense presentation slides.
Jul '19   I attended the IJCAI-19 conference in Macau, and presented a main-track paper titled, "Bayesian Inference of Linear Temporal Logic Specifications for Contrastive Explanations" in the Search in Planning and Scheduling Track.
Jul '19   I attended the ICAPS-19 conference and presented a workshop paper on contrastive LTL mining at the Explainable AI Planning (XAIP) session.
Jan '19   I gave an invited talk at IBM Research AI (Cambridge, MA), titled, "Mining Contrastive Temporal Patterns from System Traces."
Jul '18   I presented my full paper, "Learning to Infer Final Plans in Human Team Planning", at IJCAI-18 Conference held in Stockholm, Sweden.
Jul '18   I received a travel award to particiate in the IJCAI-18 Doctoral Consortium, which was collocated with ICML and AAMAS conferences at Stockhom, Sweden.
May '18   I worked as a research intern at MIT-IBM Watson AI Lab and collaborated with Dr. Christian Muise on inducing temporal specifications from system logs.