Author

Beomsu Kim

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

MaDeL: Manifold-Decomposed Feature Losses for Generative Modeling

Generative models are often trained with isotropic objectives such as mean-squared error. For data concentrated near a low-dimensional manifold, however, such losses conflate displacement along the manifold, which may represent valid variation, with displacement away from it, which produces invalid samples. This mismat...

Beomsu Kim, Jong Chul Ye, Kwanyoung Kim · 0 citations

#artificial intelligence Preprint Sep 2026

Learning What to Recall: Adaptive Multi-Cue Episodic Memory for World Models

World models predict future observations from current experience and actions, yet prediction can depend on observations seen far in the past. Episodic memory preserves past observations for later recall; however, as memory accumulates, it raises a fundamental question: which memories are useful for the current predicti...

Beomsu Kim, Chieh-Hsin Lai, Bac Nguyen et al. · 0 citations