3 citations · 3 across the 6 of their papers we have counts for
6 papers
The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models
Dueun Kim, Albert No
Chain-of-thought reasoning helps autoregressive models solve complex problems by generating intermediate steps that support later predictions. Masked diffusion models (MDMs) offer…
Memorization In Stable Diffusion Is Unexpectedly Driven by CLIP Embeddings
Bumjun Kim, Albert No
Understanding how textual embeddings contribute to memorization in text-to-image diffusion models is crucial for both interpretability and safety. This paper investigates an unexpe…
Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Model
Joo Young Choi, Jaesung R. Park, Inkyu Park +3
Current state-of-the-art diffusion models employ U-Net architectures containing convolutional and (qkv) self-attention layers. The U-Net processes images while being conditioned on…
Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback
TaeHo Yoon, Kibeom Myoung, Keon Lee +3
Diffusion models have recently shown remarkable success in high-quality image generation. Sometimes, however, a pre-trained diffusion model exhibits partial misalignment in the sen…
Neural Tangent Kernel Analysis of Deep Narrow Neural Networks
Jongmin Lee, Joo Young Choi, Ernest K. Ryu +1
The tremendous recent progress in analyzing the training dynamics of overparameterized neural networks has primarily focused on wide networks and therefore does not sufficiently ad…
WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points
Albert No, TaeHo Yoon, Sehyun Kwon +1
Generative adversarial networks (GAN) are a widely used class of deep generative models, but their minimax training dynamics are not understood very well. In this work, we show tha…