# CLOVA & AI Lab @ ICML 2022

![](/files/iCJkCCgyTERbCaYzPMCl)

## Main Track

### July 19, Tue

<mark style="color:purple;">**Spotlight 10:50**</mark>\
**Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation**.\
Giung Nam · Hyungi Lee · Byeongho Heo · Juho Lee

<mark style="color:purple;">**Spotlight 11:45**</mark>\
**Time Is MattEr: Temporal Self-supervision for Video Transformers**. \
\&#xNAN;*Sukmin Yun · Jaehyung Kim · Dongyoon Han · Hwanjun Song · Jung-Woo Ha · Jinwoo Shin*

<mark style="color:purple;">**Poster 15:30**</mark>\
**Time Is MattEr: Temporal Self-supervision for Video Transformers**. \
\&#xNAN;*Sukmin Yun · Jaehyung Kim · Dongyoon Han · Hwanjun Song · Jung-Woo Ha · Jinwoo Shin*

**Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation**.\
Giung Nam · Hyungi Lee · Byeongho Heo · Juho Lee<br>

### July 21, Thu

<mark style="color:purple;">**Spotlight 07:30**</mark>\
**Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness.** \
Namuk Park · Songkuk Kim

<mark style="color:purple;">**Spotlight 08:20**</mark>\
**Dataset Condensation via Efficient Synthetic-Data Parameterization**.\
\&#xNAN;*Jang-Hyun Kim · Jinuk Kim · Seong Joon Oh · Sangdoo Yun · Hwanjun Song · Joonhyun Jeong · Jung-Woo Ha · Hyun Oh Song*

<mark style="color:purple;">**Spotlight 08:35**</mark>\
**Dataset Condensation with Contrastive Signals***.* \
\&#xNAN;*Saehyung Lee · Sanghyuk Chun · Sangwon Jung · Sangdoo Yun · Sungroh Yoon*

<mark style="color:purple;">**Poster 15:00**</mark>\
**Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness.** \
Namuk Park · Songkuk Kim

**Dataset Condensation via Efficient Synthetic-Data Parameterization**.\
\&#xNAN;*Jang-Hyun Kim · Jinuk Kim · Seong Joon Oh · Sangdoo Yun · Hwanjun Song · Joonhyun Jeong · Jung-Woo Ha · Hyun Oh Song*

**Dataset Condensation with Contrastive Signals***.* \
\&#xNAN;*Saehyung Lee · Sanghyuk Chun · Sangwon Jung · Sangdoo Yun · Sungroh Yoon*

## Workshops

### July 22, Fri

<mark style="color:purple;">**Workshop on Spurious Correlations, Invariance, and Stability (SCIS)**</mark>\
**SelecMix: Debiased Learning by Mixing up Contradicting Pairs.**\
\&#xNAN;*Inwoo Hwang, Sangjun Lee, Yunhyeok Kwak, Seong Joon Oh, Damien Teney, Jin-Hwa Kim, Byoung-Tak Zhang.*\
Poster session: 13:30 - 14:50 (Poster ID: #3)

<mark style="color:purple;">**Workshop on ReALML (Adaptive Experimental Design and Active Learning in the Real World)**</mark>\
**LG-FAL: Federated Active Learning Strategy using Local and Global Models.**\
\&#xNAN;*SangMook Kim, SangMin Bae, Se-Young Yun, Hwanjun Song.*\
Poster session: 15:30pm-17:30pm

### July 23, Sat

<mark style="color:purple;">**Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward (Pre-training)**</mark>\
**Generative Self-training Improves Pre-training for Visual Dialog.**\
\&#xNAN;*Gi-Cheon Kang, Sungdong Kim, Jin-Hwa Kim, Donghyun Kwak, Byoung-Tak Zhang*.\
Poster session: 15:00 - 16:30

<mark style="color:purple;">**Workshop on UpML (Updatable Machine Learning)**</mark>\
**ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning.**\
\&#xNAN;*Jaehoon Oh\*, Sungnyun Kim\*, Namgyu Ho\*, Jin-Hwa Kim, Hwanjun Song, Se-Young Yun.*\
Poster session: 17:05pm-19:30pm


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://naver-career.gitbook.io/en/teams/clova-cic/events/clova-and-ai-lab-icml-2022.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.