6 papers
Towards Spatially Consistent Image Generation: On Incorporating Intrinsic Scene Properties into Diffusion Models
Hyundo Lee, Suhyung Choi, Inwoo Hwang +1
Image generation models trained on large datasets can synthesize high-quality images but often produce spatially inconsistent and distorted images due to limited information about…
From Black-box to Causal-box: Towards Building More Interpretable Models
Inwoo Hwang, Yushu Pan, Elias Bareinboim
Understanding the predictions made by deep learning models remains a central challenge, especially in high-stakes applications. A promising approach is to equip models with the abi…
SnapMoGen: Human Motion Generation from Expressive Texts
Chuan Guo, Inwoo Hwang, Jian Wang +1
Text-to-motion generation has experienced remarkable progress in recent years. However, current approaches remain limited to synthesizing motion from short or general text prompts,…
Towards Causal Representation Learning with Observable Sources as Auxiliaries
Kwonho Kim, Heejeong Nam, Inwoo Hwang +1
Causal representation learning seeks to recover latent factors that generate observational data through a mixing function. Needing assumptions on latent structures or relationships…
Locality-aware Concept Bottleneck Model
Sujin Jeon, Hyundo Lee, Eungseo Kim +3
Concept bottleneck models (CBMs) are inherently interpretable models that make predictions based on human-understandable visual cues, referred to as concepts. As obtaining dense co…
PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization
Dong Kyu Cho, Inwoo Hwang, Sanghack Lee
Data augmentation is a popular tool for single source domain generalization, which expands the source domain by generating simulated ones, improving generalization on unseen target…