We are uploading a recorded video on personal youtube storage. please check the link below.
Objective: Paper reading/discussion on VL models (not limited to md (medical domain); md -> gd (general domain) -> md -> gd ...)
Time: Thur 10:30 AM - 11:30 AM
Agenda: 1 people present for about 40 min / the rest is the discussion.
Participants : 종학, 현경, 성수
| Publish | AKA | Paper | Topic | TL;DR | Link | Review |
|---|---|---|---|---|---|---|
| arxiv 23 / MS | BioViL-T | Learning to Exploit Temporal Structure for Biomedical Vision–Language Processing | parametric model | prior study, vision-language encoder, BERT-like decoder, VLM + LLM | Paper | Jonghak (week1) |
| Date | Week | Presenter | Topic | Paper | Material | Link |
|---|---|---|---|---|---|---|
| 2023.04.06 | Week01 | Jonghak | parametric model | BioViL-T | Slides |