E-mail: robinjia at stanford dot edu
I am a fourth-year Ph.D. student in Computer Science at Stanford University. My advisor is Percy Liang, and my current research focus is on natural language processing and machine learning. In the past, I have also worked on various projects in computational biology. I am supported by an NSF Graduate Research Fellowship.
Previously, I was an undergraduate at Stanford University, from which I received a B.S. with Honors in Computer Science and a Minor in Biology in June 2014.
Adversarial Examples for Evaluating Reading Comprehension Systems.
Robin Jia and Percy Liang.
Empirical Methods in Natural Language Processing (EMNLP), 2017.
Outstanding Paper Award.
(pdf) (bib) (codalab)
Learning Concepts through Conversations in Spoken Dialogue Systems.
Robin Jia, Larry Heck, Dilek Hakkani-Tür, and Georgi Nikolov.
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2017.
(pdf) (bib) (data)
"Reverse genomics" predicts function of human conserved noncoding elements.
Amir Marcovitz, Robin Jia, and Gill Bejerano.
Molecular Biology and Evolution, 2016.
Mx1 and Mx2 key antiviral proteins are surprisingly lost in toothed whales.
Benjamin A. Braun, Amir Marcovitz, J. Gray Camp, Robin Jia, and Gill Bejerano.
Proceedings of the National Academy of Sciences (PNAS), 2015.
Forward Genomics for Conserved Noncoding Elements with Gray Camp, Amir Marcovitz, and Gill Bejerano.
Starting in October of 2012, I worked on computational genomics research with Professor Gill Bejerano. I developed a computational pipeline to predict function of conserved noncoding elements by using their evolutionary histories to match them with known traits. I completed my undergraduate honors thesis with Professor Bejerano as my advisor. (poster)
Automated Gating of Flow Cytometry Data with Robert Bruggner, Rachel Finck, Noah Zimmerman, and David Dill.
Starting in June of 2011, I worked with Professor David Dill's group on automated clustering ("gating") of high-dimensional flow cytometry data. Our work was presented at the Flowcap-II summit. (presentation, poster)
- Teaching. In the Fall of 2015, I was the head TA for CS221, Stanford's introductory artificial intelligence class. I led a team of 18 TAs for a class with 550 enrolled students.
- Google. I have spent three summers as an intern at Google Mountain View. In 2016, I worked with Larry Heck, Georgi Nikolov, and Dilek Hakkani-Tür on the Deep Dialogue team at Google Research, exploring how to build task-based dialogue systems that can learn from personalized user feedback. In 2014, I worked on the Crisis Response Team within the Social Impact arm of Google, where I built infrasturcutre to automatically launch informational pages about hurricanes and tropical storms for people in affected areas. In 2012, I worked on the YouTube Ads team on a machine learning project to understand user behavior on the YouTube search page.
- CS106 Section Leading. I was a section leader for Stanford's CS106A (Introduction to Programming) class in the Winter of 2012. I led weekly 50-minute sections, assisted students, graded assignments, and helped maintain some of our internal grading scirpts.
- Tutoring. In the past, I have volunteered at the SUMO as a Math 50's Series Tutor. I also ran the tutoring program during the 2011-2012 school year.
When I'm not coding, I spend a good amount of my time playing the piano. For a long time, I studied piano with with Angela Wright of Oak Park, Illinois. Since coming to Stanford in 2010, my teacher has been Laura Dahl.
Here are some of my recordings:
- Mendelssohn: Capriccio Brillante, Op. 22
As one of the three winners of my high school's concerto competition, I had the great privilege of playing this piece with my high school orchestra. The video is broken up into two parts on YouTube: Part 1, Part 2.
- Schumann: Toccata, Op. 7
From a practice session, while I was preparing for a master class with (the amazing) Jon Nakamatsu in 2013. (m4a)
The next four recordings are from my Stanford senior recital on April 12, 2014. Some parts of this recital could have definitely gone better, but I'm also quite happy with many aspects of my performance. If you're going to listen to one thing here, I think the Debussy probably came out the best.
- Mozart: Sonata in B-Flat, K 281 (m4a for Mov. 1, Mov. 2, Mov. 3)
- Chopin: Ballade No. 1 in G Minor (m4a)
- Debussy: L'Isle Joyeuse (m4a)
- Liszt: Sonata in B Minor (m4a)
- Stanford Math Tournament. Throughout my time at Stanford, I have helped organize the Stanford Math Tournament, a high school math tournament created and run by Stanford students. I was the primary editor of the Geometry Test in 2011 and 2012, the Calculus Test in 2013, and the Team Test in 2014. I was also the primary developer for our online registration website.
- Set. A Java applet for the popular card game Set that I built with Jack Chen and Nick Wu.