Yeongtak Oh

Contextualized Visual Personalization in Vision-Language Models

Yeongtak Oh*, Sangwon Yu*, Junsung Park, Han Cheol Moon, Jisoo Mok, and Sungroh Yoon

* Equal contribution

Forty-Third International Conference on Machine Learning (ICML), 2026

Project Page Arxiv ArXivLens

We introduce CoViP, a unified framework for contextualized visual personalization in VLMs, featuring a novel personalized image captioning benchmark, an RL-based post-training scheme, and diagnostic downstream personalization tasks.

Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment

Sangha Park, Eunji Kim, Yeongtak Oh, Jooyoung Choi, and Sungroh Yoon

The IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026

OpenReview

We introduce Negative Prompting for Image Correction (NPC), an automated pipeline for using negative prompts to enhance image-text alignment.

Style-Friendly SNR Sampler for Style-Driven Generation

Jooyoung Choi*, Chaehun Shin*, Yeongtak Oh, Heeseung Kim, Jungbeom Lee, and Sungroh Yoon

* Equal contribution

The IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026

Project Page Arxiv

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.

RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models

Yeongtak Oh, Dohyun Chung, Juhyeon Shin, Sangha Park, Johan Barthelemy, Jisoo Mok†, and Sungroh Yoon†

† Equal corresponding

Neural Information Processing Systems (NeurIPS)

Selected as a WINNER in Qualcomm Innovation Fellowship Korea (QIFK) 2025 (Link)

Project Page Arxiv

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: Stylized 3D Generation with Multi-View ControlNet

Yeongtak Oh*, Jooyoung Choi*, Yongsung Kim, Minjun Park, Chaehun Shin, and Sungroh Yoon

* Equal contribution

British Machine Vision Conference (BMVC)

Project Page Arxiv

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

Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation

Yeongtak Oh*, Jonghyun Lee*, Jooyoung Choi, Dahuin Jung, Uiwon Hwang†, and Sungroh Yoon†

* Equal contribution, † Equal corresponding

European Conference on Computer Vision (ECCV)

Project Page Arxiv

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

On mitigating stability-plasticity dilemma in CLIP-guided image morphing via geodesic distillation loss

Yeongtak Oh, Saehyung Lee, Uiwon Hwang†, and Sungroh Yoon†

† Equal corresponding

International Journal of Computer Vision (IJCV), IF: 11.6

Project Page Arxiv

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