Yeongtak Oh

He is a Ph.D. Candidate in the DSAIL Lab at Seoul National University, Seoul, South Korea. His research focuses on computer vision with particular interests in generative models, personalization, and vision–language models. He received his B.S. degree in Mechanical Engineering from Seoul National University, Seoul, Korea, in 2018, and his M.S. degree in the same department in 2020. In 2021, he served as a Military Science and Technology Researcher at the Korea Military Academy AI R&D Center.

Email  /  CV  /  Google Scholar  /  Github

ControlDreamer enables high-quality 3D generation with creative geometry and styles via multi-view ControlNet.

We propose Decorruptor to enhance the robustness of the diffusion model and accelerate the diffusion-based image-level updates.

We have enhanced a range of CLIP-guided image morphing baselines through the implementation of our proposed inter- and intra-modality regularization losses, effectively addressing the SP dilemma.

We present a deep learning-based motion-adaptive fault detection method for industrial robots using torque ripples.

We propose RePIC, a reinforced post-training framework that outperforms SFT-based methods in multi-concept personalized image captioning by enhancing visual recognition and generalization through reward templates and curated instructions.

We propose the Style-friendly SNR sampler, which aggressively shifts the signal-to-noise ratio (SNR) distribution toward higher noise levels during fine-tuning to focus on noise levels where stylistic features emerge.

This page is borrowed from Jon Barron's webpage.