Generation Research

Generation Research at NAVER AI Lab

We contribute to the global development of AI technology by pushing the boundaries of visual generation and supporting users' creative activities by providing high-quality generations. Furthermore, it enables new business models by leveraging the power of AI generation to create virtual characters, objects, and environments. We welcome strong candidates with diverse research experiences and leadership skills, having publications presented at top-tier venues. Join us on the journey of innovation and excellence!

Our research interests include:

  • Multimodal generation models

  • Neural 3D representation learning and its applications

  • Generative applications tailored for LLMs

Hiring Research Scientists

We are seeking globally competitive research scientists to join our team and work on advancing generation research. As an individual research scientist, you will have the opportunity to lead your own research projects and collaborate on international projects with our associate research centers.

What you will do:

  • Research and develop novel methods related to 2D/3D generations

  • Publish original papers to top-tier academic venues

  • Collaborate with our colleague researchers and mentor interns

  • Communicate and collaborate with prominent external researchers

Requirements

  • Holds a PhD degree or equivalent (or expected to receive within 6 months) in Computer Science (CS), Electrical Engineering (EE), or other relevant fields

  • Academic publication records at top-tier conferences and journals in Machine Learning and Computer Vision

  • Comprehensive experience in research collaborations and academic writing in related fields

  • Excellent communication skills

How to Apply

  • Please submit your application via this platform to register for our Talent Pool (available in Korean/ English), where sign-in is required.

    • Application category: Tech > Common > Common > AI (Full-time)

    • Please be advised that the hiring process could extend up to three months. If you have a deadline for another offer, we encourage you to reach out to HR for further assistance.

Hiring Research Interns

We are hiring around three research interns per half-year. As an intern, you will participate in a research project aimed at one of the top-tier publication venues. You may also participate in other projects and engage in discussions to broaden your research experience.

What you will be doing:

  • Explore and conduct research to publish a solid work

  • Study and share relevant works

  • Communicate and collaborate with team members

Requirements

  • Pursuing a M.S/PhD or equivalent in Computer Science (CS), Electrical Engineering (EE), or other relevant fields

  • Experience as a lead author for a top-tier venue

  • Have at least six months before their graduation

How to Apply

  • Please submit your application via this platform to register for our Talent Pool (available in Korean/English), where sign-in is required.

    • Application category: Tech > Common > Common > AI (Intern)

Internship Alumni

2024

2023

2022

Publications

NAVER AI Lab employees are distinguished by being displayed in bold text. The equal contributions and co-corresponding authors are denoted by asterisks (*) and carets (^), respectively. When a single author takes the lead and the last author signifies the corresponding author, we omit the notation briefly.

2024

  1. Polyhedral Complex Derivation from Piecewise Trilinear Networks. Jin-Hwa Kim (NAVER AI Lab, SNU AIIS). NeurIPS 2024. [arXiv][Demo]

  2. Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting. Junha Hyung (KAIST), Susung Hong (Korea Univ.), Sungwon Hwang (KAIST), Jaeseong Lee (KAIST), Jaegul Choo^ (KAIST), Jin-Hwa Kim^ (NAVER AI Lab, SNU AIIS). NeurIPS 2024. [arXiv][Project]

  3. Diffusion Unlearning Optimization for Robust and Safe Text-to-Image Models. Yong-Hyun Park (SNU), Sangdoo Yun (NAVER AI Lab, SNU AIIS), Jin-Hwa Kim (NAVER AI Lab, SNU AIIS), Junho Kim (NAVER AI Lab), Geonhui Jang (Korea Univ.), Yonghyun Jeong (NAVER Cloud), Junghyo Cho^ (SNU, KIAS), Gayoung Lee^ (NAVER AI Lab). ICML 2024 GenLaw Workshop, & NeurIPS 2024. [arXiv]

  4. Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback. Fatemeh Pesaran zadeh (SNU), Juyeon Kim (KAIST), Jin-Hwa Kim (NAVER AI Lab, SNU AIIS), Gunhee Kim (SNU). EMNLP 2024 Oral.

  5. D-Cube: Exploiting Hyper-Features of Diffusion Model for Robust Medical Classification. Minhee Jang* (Ewha Univ.), Juheon Son* (Ewha Univ.), Thanaporn Viriyasaranon (Ewha Univ.), Junho Kim^ (NAVER AI Lab), Jang-Hwan Choi^ (Ewha Univ.). ICDM 2024.

  6. Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields: Execution on Edge-Devices. Jun-Seong Kim* (POSTECH), Mingyu Kim* (University of British Columbia), GeonU Kim (POSTECH), Tae-Hyun Oh^ (POSTECH), Jin-Hwa Kim^ (NAVER AI Lab, SNU AIIS). The IEEE Robotics and Automation Letters (RA-L).

  7. Visual Style Prompting with Swapping Self-Attention. Jaeseok Jeong* (Yonsei Univ.), Junho Kim* (NAVER AI Lab), Yunjey Choi (NAVER AI Lab), Gayoung Lee (NAVER AI Lab), Youngjung Uh (Yonsei Univ.), arXiv 2024. AI4CC 2024 Best Paper. 🥇 [arXiv][Project][Demo]

  8. Geometry-Aware Score Distillation via 3D Consistent Noising and Gradient Consistency Modeling. Min-Seop Kwak (Korea Univ.), Donghoon Ahn (Korea Univ.), Ines Hyeonsu Kim (Korea Univ.), Jin-Hwa Kim^ (NAVER AI Lab, SNU AIIS), Seungryong Kim^ (Korea Univ.), arXiv 2024. [arXiv][Project]

  9. A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models. Taehong Moon (KRAFTON), Moonseok Choi (KAIST), EungGu Yun (KAIST), Jongmin Yoon (KAIST), Gayoung Lee (NAVER AI Lab), Jaewoong Cho (KRAFTON), Juho Lee (KAIST). ICML 2024.

  10. Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs, Mingyu Kim (KAIST), Jun-Seong Kim (POSTECH), Se-Young Yun^ (KAIST), Jin-Hwa Kim^ (NAVER AI Lab, SNU AIIS), ICML 2024.

  11. PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency, Yeonsung Jung (KAIST), Heecheol Yun (KAIST), Joonhyung Park (KAIST), Jin-Hwa Kim^ (NAVER AI Lab, SNU AIIS), Eunho Yang^ (KAIST), ICML 2024.

  12. Vision-Language Generative Model for View-Specific Chest X-ray Generation, Hyungyung Lee (KAIST), Da Young Lee (Deep-in-Sight Co.), Wonjae Kim (NAVER AI Lab), Jin-Hwa Kim (NAVER AI Lab, SNU AIIS), Tackeun Kim (Seoul National Bundang Hospital), Jihang Kim (Seoul National Bundang Hospital), Leonard Sunwoo (Seoul National Bundang Hospital), Edward Choi (KAIST), CHIL 2024.

  13. Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation. Junyoung Seo* (Korea Univ.), Wooseok Jang* (Korea University), Min-Seop Kwak* (Korea Univ.), Hyeonsu Kim (Korea University), Jaehoon Ko (Korea University), Junho Kim (NAVER AI Lab), Jin-Hwa Kim^ (NAVER AI Lab, SNU AIIS), Jiyoung Lee^ (NAVER AI Lab), Seungryong Kim^ (Korea Univ.). ICLR 2024. [Paper][Project][Code][Threestudio]

2023

  1. 3D-aware Blending with Generative NeRFs. Hyunsu Kim (NAVER AI Lab), Gayoung Lee (NAVER AI Lab), Yunjey Choi (NAVER AI Lab), Jin-Hwa Kim (NAVER AI Lab, SNU AIIS), Jun-Yan Zhu (CMU). ICCV 2023.

  2. Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models. Jaewoong Lee (KAIST), Sangwon Jang (Yonsei Univ.), Jaehyeong Jo (KAIST), Jaehong Yoon (KAIST), Yunji Kim (NAVER AI Lab), Jin-Hwa Kim (NAVER AI Lab, SNU AIIS), Jung-Woo Ha (NAVER AI Lab), Sung Ju Hwang (KAIST), ICCV 2023.

  3. Dense Text-to-Image Generation with Attention Modulation. Yunji Kim (NAVER AI Lab), Jiyoung Lee (NAVER AI Lab), Jin-Hwa Kim (NAVER AI Lab, SNU AIIS), Jung-Woo Ha (NAVER AI Lab), Jun-Yan Zhu (CMU). ICCV 2023.

  4. Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding. Gyeongman Kim (KAIST), Hajin Shim (KAIST), Hyunsu Kim (NAVER AI Lab), Yunjey Choi (NAVER AI Lab), Junho Kim (NAVER AI Lab), Eunho Yang (KAIST). CVPR 2023.

  5. Custom-Edit: Text-Guided Image Editing with Customized Diffusion Models. Jooyoung Choi (SNU), Yunjey Choi (NAVER AI Lab), Yunji Kim (NAVER AI Lab), Junho Kim (NAVER AI Lab). CVPR AI4CC Workshop Oral 2023.

  6. Panoramic Image-to-Image Translation. Soohyun Kim (Korea Univ.), Junho Kim (NAVER AI Lab), Taekyung Kim (NAVER AI Lab), Hwan Heo (Korea Univ.), Seungryong Kim^ (Korea Univ.), Jiyoung Lee^ (NAVER AI Lab), Jin-Hwa Kim^ (NAVER AI Lab, SNU AIIS). ArXiv 2023.

  7. Robust Camera Pose Refinement for Multi-Resolution Hash Encoding. Hwan Heo (Korea Univ.), Taekyung Kim (NAVER AI Lab), Jiyoung Lee (NAVER AI Lab), Jaewon Lee (Korea Univ.), Soohyun Kim (Korea Univ.), Hyunwoo J. Kim^ (Korea Univ.), Jin-Hwa Kim^ (NAVER AI Lab, SNU AIIS). ICML 2023.

  8. Rarity Score: A New Metric to Evaluate the Uncommonness of Synthesized Images. Jiyeon Han (KAIST), Hwanil Choi (KAIST), Yunjey Choi (NAVER AI Lab), Junho Kim (NAVER AI Lab), Jung-Woo Ha (NAVER AI Lab), Jaesik Choi (KAIST). ICLR 2023 Spotlight.

  9. Learning Input-agnostic Manipulation Directions in StyleGAN with Text Guidance. Yoonjeon Kim (KAIST), Hyunsu Kim (NAVER AI Lab), Junho Kim (NAVER AI Lab), Yunjey Choi (NAVER AI Lab), Eunho Yang (KAIST). ICLR 2023.

2022

  1. Mutual Information Divergence: A Unified Metric for Multimodal Generative Models. Jin-Hwa Kim*^ (NAVER AI Lab, SNU AIIS), Yunji Kim (NAVER AI Lab), Jiyoung Lee (NAVER AI Lab), Kang Min Yoo (NAVER AI Lab), Sang-Woo Lee (NAVER CLOVA). NeurIPS 2022.

  2. Generator Knows What Discriminator Should Learn in Unconditional GANs. Gayoung Lee (NAVER AI Lab), Hyunsu Kim (NAVER AI Lab), Junho Kim (NAVER AI Lab), Seonghyeon Kim (NAVER CLOVA), Jung-Woo Ha (NAVER AI Lab), Yunjey Choi (NAVER AI Lab). ECCV 2022.

  3. Feature Statistics Mixing Regularization for Generative Adversarial Networks. Junho Kim (NAVER AI Lab), Yunjey Choi (NAVER AI Lab), Youngjung Uh (Yonsei Univ.). CVPR 2022.

  4. Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks. Sihyun Yu (KAIST), Jihoon Tack (KAIST), Sangwoo Mo (KAIST), Hyunsu Kim (NAVER AI Lab), Junho Kim (NAVER AI Lab), Jung-Woo Ha (NAVER AI Lab), Jinwoo Shin (KAIST). ICLR 2022.

2021

  1. Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing. Hyunsu Kim (NAVER AI Lab), Yunjey Choi (NAVER AI Lab), Junho Kim (NAVER AI Lab), Sungjoo Yoo (SNU), Youngjung Uh (Yonsei Univ.). CVPR 2021.

  2. Rethinking the Truly Unsupervised Image-to-Image Translation. Kyungjune Baek (Yonsei Univ.), Yunjey Choi (NAVER AI Lab), Youngjung Uh (Yonsei Univ.), Jaejun Yoo (EPFL), Hyunjung Shim (Yonsei U.). ICCV 2021.

  3. Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing. Hyunsu Kim (NAVER AI Lab), Yunjey Choi (NAVER AI Lab), Junho Kim (NAVER AI Lab), Sungjoo Yoo (SNU), Youngjung Uh (Yonsei Univ.). CVPR 2021.

Last updated