Author

S. Karaman

h-index 61 View on Semantic Scholar

We have 2 of 274 papers

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.

#machine learning Feb 2026

Flow Matching with Uncertainty Quantification and Guidance

Uncertainty-aware flow matching (UA-Flow) is proposed, a lightweight extension of flow matching that predicts the velocity field together with heteroscedastic uncertainty that tracks sample fidelity more consistently than element-wise baselines and that these signals also carry information about data-manifold support.

Juyeop Han, Lukas Lao Beyer, Sertac Karaman · arXiv.org · 8 citations

Jul 2026

G2SR: Geometric Methods for Fast and Memory-Efficient Gaussian-based Surface Reconstruction

G2SR matches or exceeds the geometric accuracy of state-of-the-art end-to-end methods while running at 69-89 reconstructions per second within 203 MB of GPU memory (5-107x less) for 2- and 3-view inputs at 384 x 512 resolution, offering a practical path to online Gaussian-based surface reconstruction.

Da-Song Gao, Vivienne Sze, S. Karaman · arXiv.org · 0 citations