Intelligent Information Processing Lab.

Announcement

• (2024) We are pleased to share that our paper has been accepted to the AAAI 2025 (Demo Track).

  • "SummPilot: Bridging Efficiency and Customization for Interactive Summarization System"

• (2024) We are delighted to announce that three of our papers have been accepted to the EMNLP 2024 Main conference. Congratulations to all the authors on this outstanding achievement! The accepted papers are:

  • "UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation"

  • "Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation"

  • "IM-BERT: Enhancing Robustness of BERT through the Implicit Euler Method"

• (2024) We are delighted to announce that our paper, led by Soojin Jang, has been accepted to ECCV 2024. Congratulations to Soojin on this outstanding achievement! - "DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation" (Link)

• (2024) We are delighted to announce that our paper, led by Seunguk Yu, has been accepted to the Findings of NAACL 2024. Congratulations, Seunguk, on this excellent work! - "Don't be a Fool: Pooling Strategies in Offensive Language Detection from User-Intended Adversarial Attacks" (Link)

• (2024) Our paper has been accepted to COLING 2024. - "Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation" (Link)

• (2024) Our paper has been accepted to the ICLR 2024 Tiny Papers track for an oral presentation. - "Colorful Cutout: Enhancing Image Data Augmentation with Curriculum Learning" (Link)

• (2024) We are pleased to inform that our paper, led by Juhwan Choi, has been accepted to the Findings of EACL 2024. Congratulations to Juhwan on this achievement! - "GPTs Are Multilingual Annotators for Sequence Generation Tasks" (Link)

• (2024) We'd like to share the acceptance of a paper by Juhwan Choi to the EACL 2024 Student Research Workshop. - "AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimes" (Link)

• (2024) We are happy to share that our paper, led by JuneHyoung Kwon, has been accepted to WACV 2024. Well done, JuneHyoung! - "Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation" (Link)

• (2023) We are pleased to announce that our paper, led by Jungmin Yun, has been accepted to the Findings of EMNLP 2023 and will be presented in-person at the SpLU-RoboNLP workshop. Congratulations to Jungmin on this achievement! - "Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification" (Link)

• (2023) Our paper has been accepted for an oral presentation in the Tiny Papers track at ICLR 2023 - "SoftEDA: Rethinking Rule-Based Data Augmentation with Soft Labels" (Link)

• Our research team is actively engaged in addressing the unique challenges presented by low-resource environments through AI research. Under the guidance of experienced researchers, we focus on areas like data augmentation, language processing, and enhancing the efficiency of AI systems. Our collaborative efforts have led to recognition at several international conferences, including EMNLP, NAACL, COLING, ICLR, EACL, and WACV.

  • To apply, please send a short introduction and your Curriculum Vitae to Professor Youngbin Kim at ybkim85@cau.ac.kr.

Our Research Vision in Low-Resource Environments

Our lab is dedicated to addressing the challenges and leveraging the opportunities within low-resource environments, pioneering efficient, innovative solutions across data augmentation, language processing, and AI efficiency. Our mission is to democratize AI technologies, ensuring advancements are accessible and beneficial universally, particularly in contexts where resources are scarce but the potential for impact is immense.

Research Focus Areas within the Low-Resource Framework

1. Language Processing in Low-Resource Languages

- Our research advances multilingual and low-resource language processing, aiming to create inclusive language technologies that cater to a wide array of languages and dialects, improving accessibility and utility across diverse linguistic landscapes.

2. Data Augmentation for Low-Resource Scenarios

- We focus on innovative image and text data augmentation techniques tailored for overcoming data scarcity, employing strategies like curriculum learning to incrementally enhance model robustness and performance with minimal resources.

3. Enhancing AI Efficiency for Low-Resource Applications

- We explore methods to increase the efficiency and robustness of AI models in environments with limited computational and data resources, including model compression techniques and robust training approaches that ensure sustainability and practicality in real-world applications.

By focusing on the unique challenges of low-resource environments, our lab not only contributes to the broader AI and machine learning community but also ensures that our research has a tangible impact on making AI technologies more accessible and equitable across the globe. Our commitment to this area reflects our belief that the most significant advancements in AI will come from solutions that address real-world limitations and strive for inclusivity and broad applicability.