SS

Soowon Son

cs.CV

On Valency

published · living versions

W_77a6zhfy·v1 · currentpublished

DreamX: Video Diffusion Model is a Universal Latent Action Learner

with Jisoo Kim, Chaehyun Kim, Junsu Kim, Jiho Park +4

1 version

Preprints & journals

5 papers in the corpus · 2024–2026

TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking2605.12587v1 · Jisu Nam, Jahyeok Koo, Soowon Son et al.2026 · 0 citationsarXiv

TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation2603.23487v1 · Jini Yang, Eunbeen Hong, Soowon Son et al.2026 · 0 citationsarXiv

Probing and Leveraging Video Diffusion Transformer Features for Robust Point Tracking2512.20606v2 · Soowon Son, Honggyu An, Jisu Nam et al.2025 · 0 citationsarXiv

Emergent Temporal Correspondences from Video Diffusion Transformers2506.17220v2 · Jisu Nam, Soowon Son, Dahyun Chung et al.2025 · 1 citationarXiv

Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification2406.16042v3 · Ines Hyeonsu Kim, Woojeong Jin, Soowon Son et al.2024 · 0 citationsarXiv

Career total: 7 works. 5 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.