Junghyo Jo

2 papers · 2023–2024 · 1 venue · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird

Venues

NeurIPS (2)

Top co-authors

Yong-Hyun Park (2) Sangdoo Yun (1) Jaewoong Choi (1) Gayoung Lee (1) Geonhui Jang (1) Youngjung Uh (1) Jin-Hwa Kim (1) Junho Kim (1) Yonghyun Jeong (1) Mingi Kwon (1)

Research topics

Deep Learning (2) Learning Types · Deep Learning (2) Models (2) Artificial Intelligence (1) Computer Science (1) Computer Vision (1) Machine Learning (1) Application Areas (1) Applications (1) Core AI (1) Generation (1) Learning Types · Machine Learning (1) Processing (1)

Keywords

preference optimization (1) image editing (1) text-to-image generation (1) model safety (1) machine unlearning (1) riemannian geometry (1) adversarial attack (1) generative model (1) diffusion model (1) latent space (1) text-to-image model (1) content safety (1) pullback metric (1) latent space analysis (1)

Papers

Direct Unlearning Optimization for Robust and Safe Text-to-Image Models NeurIPS 2024 Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry NeurIPS 2023