6 papers
Persistence Positional Encoding: A Minimal Transformer Recipe for Persistence Diagrams
Eunwoo Heo, Ganghyun Kim, Jaejun Yoo
Persistence diagrams (PDs) represent multiscale topological information as multisets of birth-death pairs . How best to use them with Transformers, however, remains unclear.…
LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models
Hyunsoo Han, Sangyeop Yeo, Jaejun Yoo
We demonstrate that in knowledge distillation for diffusion models, the teacher network's highly complex denoising process - stemming from its substantially larger capacity - poses…
What Linear Probes Miss: Multi-View Probing for Weight-Space Learning
Eunwoo Heo, Kyeongkook Seo, Jaejun Yoo
The explosive growth of open-source model repositories has created a Model Jungle, where checkpoints are frequently shared without adequate documentation or metadata. While weight-…
On the Reliability of Cue Conflict and Beyond
Pum Jun Kim, Seung-Ah Lee, Seongho Park +2
Understanding how neural networks rely on visual cues offers a human-interpretable view of their internal decision processes. The cue-conflict benchmark has been influential in pro…
PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models
Kyeongkook Seo, Dong-Jun Han, Jaejun Yoo
Despite recent advancements in federated learning (FL), the integration of generative models into FL has been limited due to challenges such as high communication costs and unstabl…
Understanding Flatness in Generative Models: Its Role and Benefits
Taehwan Lee, Kyeongkook Seo, Jaejun Yoo +1
Flat minima, known to enhance generalization and robustness in supervised learning, remain largely unexplored in generative models. In this work, we systematically investigate the…