Publications

(C: conference / W: workshop / J: journal / P: preprint) (* = equal contribution)

[C14] What to Perturb, How to Propagate: A Graph-Guided Transferable Attack on VLP Models (appear)

• Yongjae Kim, Sungbin Park, Hoon Ji, Sukmin Yun, Yeonjoon Lee

• Conference on Neural Information Processing Systems (NeurIPS) 2026

[C13] Implicit 4D Gaussian Splatting for Fast Motion with Large Inter-Frame Displacements (code, site)

• Seung-gyeom Kim, Areum Kim, Yongjae Yoo, Sukmin Yun 

• International Conference on Learning Representations (ICLR) 2026

[C12] GMAIL: Generative Modality Alignment for generated Image Learning (code)

• Shentong Mo, Sukmin Yun 

• International Conference on Machine Learning (ICML) 2025 (Spotlight Poster, 313/12107=2.59%)

[C11] PPT: Patch Order Do Matters In Time Series Pretext Task (code)

• Jaeho Kim, Kwangryeol Park, Sukmin Yun, Seulki Lee

• International Conference on Learning Representations (ICLR) 2025

[C10] Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs (code, site)

• Sukmin Yun, Haokun Lin, Rusiru Thushara, Mohammad Qazim Bhat, Yongxin Wang, Zutao Jiang, Mingkai Deng, Jinhong Wang, Tianhua Tao, Junbo Li, Haonan Li, Preslav Nakov, Timothy Baldwin, Zhengzhong Liu, Eric P Xing, Xiaodan Liang, Zhiqiang Shen

• Conference on Neural Information Processing Systems (NeurIPS, Datasets and Benchmarks Track) 2024 

[C9] TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation (code)

• Seong Hyeon Park, Huiwon Jang, Byungwoo Jeon, Sukmin Yun, Paul Hongsuck Seo, Jinwoo Shin

• Conference on Neural Information Processing Systems (NeurIPS) 2024 (Spotlight Presentation, 326/15671=2.08%)

[C8] Tabular Transfer Learning via Prompting LLMs (code)

• Jaehyun Nam, Woomin Song, Seong Hyeon Park, Jihoon Tack, Sukmin Yun, Jaehyung Kim, Kyu Hwan Oh, Jinwoo Shin

• Conference on Language Modeling (COLM) 2024

[C7] Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs (code)

• Woomin Song*, Seunghyuk Oh*, Sangwoo Mo, Jaehyung Kim, Sukmin Yun, Jung-Woo Ha, and Jinwoo Shin

• International Conference on Learning Representations (ICLR) 2024

[C6] IFSeg: Image-free Semantic Segmentation via Vision-Language Model (code)

• Sukmin Yun*, Seong Hyeon Park*, Paul Hongsuck Seo and Jinwoo Shin

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023

[C5] Time Is MattEr: Temporal Self-supervision for Video Transformers (code)

• Sukmin Yun, Jaehyung Kim, Dongyoon Han, Hwanjun Song, Jung-Woo Ha and Jinwoo Shin 

• International Conference on Machine Learning (ICML) 2022

[C4] TSPipe: Learn from Teacher Faster with Pipelines (code)

• 1. • Hwijoon Lim, Yechan Kim, Sukmin Yun, Jinwoo Shin and Dongsu Han

     • International Conference on Machine Learning (ICML) 2022

[C3] Patch-level Representation Learning for Self-supervised Vision Transformers (code) 

• Sukmin Yun, Hankook Lee, Jaehyung Kim and Jinwoo Shin 

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022 (Oral Presentation, 342/8262=4.14%)

[C2] Regularizing Class-wise Predictions via Self-knowledge Distillation (code) 

• Sukmin Yun*, Jongjin Park*, Kimin Lee and Jinwoo Shin

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020 

[C1] Robust Inference via Generative Classifiers for Handling Noisy Labels (code) 

• Kimin Lee, Sukmin Yun, Kibok Lee, Honglak Lee, Bo Li and Jinwoo Shin

• International Conference on Machine Learning (ICML) 2019 (Long Oral Presentation, 159/3424=4.64%)

[W1] OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data (code)

• Jongjin Park*, Sukmin Yun*, Jongheon Jeong and Jinwoo Shin

  1. • L2ID Workshop at European Conference on Computer Vision (ECCV) 2022