Category Archives: Uncategorized

AMLaP conference at Potsdam 9/3-9/5

The AMLaP conference (, one of the largest European conferences on human language processing, will be held on 9/3-9/5 virtually. Adina Camelia Bleotu, Brian Dillon, Bethany Dickerson, and Michael Wilson, all at UMass currently or previously, will be presenting. Registration is free. Details of the program can be found on their website.

Neural networks and sentence processing reading group Mondays at 1:30-2:30pm

Brian Dillon (UMass linguistics) and Tal Linzen (NYU) are co-organizing “Neural networks and sentence processing” reading group this semester. The meeting is held weekly on Mondays from 1:30 to 2:30pm. If you are interested in being added a the mailing list, please reach out to Brian Dillon ( Zoom link for the meeting follows:

Tung in CICS Thurs. 3/12 11:45am-1:00pm

Thursday, March 12, 2020 – 11:45 to 13:00 Hsiao-Yu (Fish) Tung (Carnegie Mellon): Embodied Visual Recognition

Abstract: Current state-of-the-art CNNs can localize and name objects in internet photos, yet, they miss the basic knowledge that a two-year-old toddler has possessed: objects persist over time despite changes in the camera view, they have 3D extent, they do not 3D intersect, and so on. In this talk, I will introduce neural architectures that learn to parse video streams of a static scene into world-centric 3D feature maps by disentangling camera motion from scene appearance. I will show the proposed architectures learn object permanence, can generate RGB views from novel viewpoints in truly novel scenes, can infer affordability in sentences by grounding language in 3D visual simulations, and can learn intuitive physics in a persistent 3D feature space. Our experiments suggest that the proposed architecture is essential to generalize across objects and locations, and it overcomes many limitations of 2D CNNs.

Bio: I received my M.S. in CMU MLD and my B.S. in Electrical Engineering from National Taiwan University in 2013. During my master, I worked with Professor Alex Smola on spectral method for Bayesian models and had succefully designed efficient and provable algorithms for topic modeling. In my undergraduate, I was one of the member in team “Algorithm @ National Taiwan University” led by Professor Chih-Jen Lin ‘s and we won the KDD CUP 2013 Championship on both Track1 and Track2.


This semester of the UMass Machine Learning and Friends Lunch (MLFL) series has been graciously sponsored by our friends at Oracle Labs.

MLFL is a lively and interactive forum held weekly where friends of the UMass Amherst machine learning community can sit down, have lunch, and give or hear a 50-minute presentation on recent machine learning research.

What is it?   A gathering of students/faculty/staff with broad interest in the methods and applications of machine learning.
When is it?    Thursdays 12:00pm to 1:00pm, unless otherwise noted. Arrive at 11:45 to get pizza.
Where is it?    CS150
Who is invited?   Everyone is welcome.
Is there food?    Yes! Pizza is provided.
Can I present?    Yes! If you would like to present your research, please email one of the organizers: Ari Kobren, Rajarshi Das, Hang Su, Samer Nashed and Aruni Roy Chowdhury

CUNY virtual conference: 3/19-3/21

The 33rd CUNY sentence processing conference, one of the largest conference on sentence processing, was planned to be take place at the UMass on 3/19-3/21. However, due to the developing coronavirus outbreak and the recommendations of the CDC and the MA Department of Public Health for large public gatherings, the conference is now going virtual! You are welcome to join the conference – see the following website for the instruction to join the conference:

Cognitive Science grant writing group forming

If you are writing an external grant this semester, or would like to support or learn from those who are, please consider joining the CogSci grant writing group. E-mail by the end of the day Sunday March 15th to join, or for more information. We will meet between biweekly and monthly. The primary focus will be to provide informal feedback to one and other on ideas and writing, but we may engage in more structured activities (e.g. workshops led by the staff at the research office) if there is interest.