I'm an Assistant Professor of Computer Science at the University of Southern California. I'm interested in robotics, computer vision, and machine learning, with a focus on robotic manipulation of visually and geometrically complex objects. These days, I'm interested in understanding how multimodal observation and action representations can lead to more sample-efficient and reliable learning. I am also interested in foundation models, and how we might be able to use them for robotic manipulation. Ultimately, I hope that this research can help open the doors for robotic manipulation in unstructured environments.
I am actively recruiting students! Please check the Sensing, Learning, and Understanding for Robotic Manipulation website to get involved. I will also hire multiple PhD students for the upcoming 2023-2024 application cycle (deadline: December 15).
Formal Bio Contact Github G. Scholar C. Vitae Research Statement
Communication Tips To International Students
Daniel Seita is an Assistant Professor in the Computer Science department at the University of Southern California and the director of the Sensing, Learning, and Understanding for Robotic Manipulation (SLURM) Lab. His research interests are in computer vision and machine learning for robot manipulation, focusing on enhancing performance in visually and geometrically challenging settings. Daniel was previously a postdoc at Carnegie Mellon University's Robotics Institute and holds a PhD in computer science from the University of California, Berkeley. He received undergraduate degrees in math and computer science from Williams College. Daniel's research has been supported by a six-year Graduate Fellowship for STEM Diversity and by a two-year Berkeley Fellowship. He has the Honorable Mention for Best Paper award at UAI 2017, was an RSS 2022 Pioneer, and has presented work at premier robotics conferences such as ICRA, IROS, RSS, and CoRL.
If you are contacting me to inquire about research opportunities, please check my lab website for more information. You do not need to email me to ask if I am taking on PhD students, and I am unable to evaluate or make decisions over email. I am much more likely to respond to emails tailored to me, in contrast to mass emails (please don't send them).
USC has an aggressive spam filter which may cause me to miss some non-USC emails, so it's OK if you want to also cc the Gmail there. (This is why some USC faculty list their Gmail as their contact information.)
There is no need to address me as "Dear Sir," "Esteemed Professor," "Respected Professor," or other excessively formal phrases that might be used in mass emails (and which I get in my inbox). You can just write "Prof. Seita," "Professor Seita," or just "Daniel." For in-person conversations, I believe my last name is pronounced like "say-ta" with two syllables.
I do my best to learn about other cultures, countries, and governments, by reading and consulting a wide variety of references. With respect to any group's political leadership, there are a range of policy issues to which I might agree or disagree. I am careful to not conflate a country's political leadership and the opinions of a citizen of that country.
I fully support people from all across the world coming to our country's schools and institutions. I think the highly international nature of Robotics and AI is one of its best qualities, and I hope it remains like this. I am not afraid to criticize or critique the U.S. government if they put up roadblocks to this. Students who come from abroad can expect to have me as an ally.
2023Moved to USC to begin my faculty career! I'm teaching CS 699 in the fall.
2022Presenting ToolFlowNet at CoRL 2022. See you in New Zealand!
2020BAIR Blog post on methods for fabric manipulation.
2018BAIR Blog post on depth sensing in robtoics.
2017Honorable Mention for Best Paper Award at UAI 2017.
2015Honored to be a recipient of the Graduate Fellowships for STEM Diversity.
2022Cornell University, Robotics Seminar (video)
2021University of Toronto, AI in Robotics Seminar (video)
Fa2024CS 699: Deep Learning for Robotic Manipulation
2024Registration Co-Chair, RSS
2023Inclusion Co-Chair, CoRL
2022Inclusion Co-Chair, CoRL
2019+Berkeley and CMU AI Mentorship Programs
2017+Primary maintainer, Berkeley AI Research Blog