Hi guys,
Welcome back! I hope you all enjoyed the first two weeks in the new
semester. So, next week’s reading discussion will be on the paper
DiffusionBERT:
Improving Generative Masked Language Models with Diffusion Models
<https://arxiv.org/abs/2211.15029>. The plan is to first revisit the basics
in diffusion models and then dive into the designs of this work that makes
it different from previous approaches. Here are some questions that might
be helpful for reading this paper:
- Is discrete diffusion possible? If so, what might be the challenges in
doing so?
- What are the major differences between image diffusion and text
diffusion?
- What are the key designs that addressed the discrete diffusion
challenges for text generation?
We will hold the discussion meeting in Torgersen 3160A, 4-5 pm on Jan 30.
Zoom discussion is also accessible through the link
https://virginiatech.zoom.us/j/5961845863.
Enjoy reading!
--
Sijia Wang
Graduate Student,
Department of Computer Science,
Virginia Tech, Blacksburg, VA 24061
Phone: +1 (314) 665 8146
Hello everyone,
We will resume our weekly reading discussion meeting from next week. It’s scheduled at 4-5pm every Monday. Everyone is more than welcome to join, either on Zoom (https://virginiatech.zoom.us/j/5961845863) or in person (Torg 3160A).
If you are interested in discussing any papers, please feel free to sign up for a time slot here: https://docs.google.com/spreadsheets/d/1LSaUY8hHcK3QzUf0iWjQT1KHk-r4SXh8av8…. You can also check the papers that we will discuss in the spreadsheet. Each presenter will also announce the papers by the last Friday before each meeting.
Look forward to seeing everyone next Monday!
Best wishes,
---------------------------------
Lifu Huang
Assistant Professor
Department of Computer Science
Virginia Tech
