[Colloquium] [TTIC Talks] 1/30 Talks at TTIC: Xin Wang, University of California, Santa Barbara

[Alicia McClarin]

*When:*      Thursday, January 30th at 11:00am



*Where:*     TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526



*Who: *       Xin Wang, University of California, Santa Barbara

*Title*:        Close the Loop Between Language and Vision for Embodied
Agents

*Abstract*: Humans learn to perceive the world through multiple modalities
including visual, auditory, and kinesthetic stimuli. The need for
perception is self-evident while humans invented language for communication
and documentation. Therefore, language and perception lay foundations for
artificial intelligence, and how to ground natural language onto real-world
perception is a fundamental challenge to empower various practical
applications that require human-machine communication.

In this talk, I will mainly present two of my research thrusts on
developing intelligent embodied agents that connect language, vision, and
actions, and that communicate with humans in the real world. First, moving
beyond natural language understanding from text-only corpora, I have
situated natural language inside interactive environments where
communication takes place. So I will discuss how to effectively ground
natural language instructions and visual inputs to actions in real-world
navigation tasks using reinforcement learning and imitation learning.
Second, in order to enable an agent to describe the visual surroundings for
humans, I will explore challenges of language generation conditioned on
visual context, and present novel solutions towards coherent and relevant
natural language descriptions. In the end, I will talk about my future
research plan.

Bio: Xin Wang is a Ph.D. candidate at the University of California, Santa
Barbara. His research interests include natural language processing,
computer vision, and machine learning, especially the intersection of
language and vision. He published over 17 papers (including 7 oral
presentations) at top NLP, CV, and ML venues such as CVPR, ICCV, ECCV, ACL,
NAACL, EMNLP, AAAI. He received the CVPR Best Student Paper Award in 2019. He
is very professionally active and organized workshops on Advances in
Language and Vision Research at ACL 2020, on Language and Vision with
Applications to Video Understanding at CVPR 2020,  and on Closing the Loop
Between Vision and Language at ICCV 2019.  He also served as a session
chair for the NLP session at AAAI 2019. He worked at Google AI and Facebook
AI Research in 2019, at Microsoft Research, Redmond in 2018, and at Adobe
Research in 2016 and 2017.

*Host: *Greg Shakhnarovich <greg at ttic.edu>

-- 
*Alicia McClarin*
*Toyota Technological Institute at Chicago*
*6045 S. Kenwood Ave., **Office 504*
*Chicago, IL 60637*
*773-834-3321*
*www.ttic.edu* <http://www.ttic.edu/>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20200123/5f6ade0a/attachment.html>