collaborators

5 papers

cs.CV2025

LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance

Jae Myung Kim, Stephan Alaniz, Cordelia Schmid +1

Despite recent advances in text-to-image generation, using synthetically generated data seldom brings a significant boost in performance for supervised learning. Oftentimes, synthe…

cs.AI2025

Feasibility with Language Models for Open-World Compositional Zero-Shot Learning

Jae Myung Kim, Stephan Alaniz, Cordelia Schmid +1

Humans can easily tell if an attribute (also called state) is realistic, i.e., feasible, for an object, e.g. fire can be hot, but it cannot be wet. In Open-World Compositional Zero…

cs.CV2025

Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Data

Yiwen Liu, Jessica Bader, Jae Myung Kim

With the development of photorealistic diffusion models, models trained in part or fully on synthetic data achieve progressively better results. However, diffusion models still rou…

cs.LG2024

Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models

Nishad Singhi, Jae Myung Kim, Karsten Roth +1

Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Crucially, the CBM design inherently allow…

cs.CV2024

DataDream: Few-shot Guided Dataset Generation

Jae Myung Kim, Jessica Bader, Stephan Alaniz +2

While text-to-image diffusion models have been shown to achieve state-of-the-art results in image synthesis, they have yet to prove their effectiveness in downstream applications.…