Yeongtak Oh

Hi, I'm a fourth-year Ph.D. candidate in ECE at Seoul National University, working in the DSAIL Lab. I research computer vision and multi-modal reasoning. My work primarily explores post-training of generative models. I'm deeply interested in advancing multi-modal AI systems in more expressive and personalized ways.

I received my B.S. (2018) and M.S. (2020) degrees in Mechanical Engineering from Seoul National University. In 2021, I served as a Military Science and Technology Researcher at the AI R&D Center of the Korea Military Academy.

Email  /  CV  /  Google Scholar  /  Github

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.

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 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.