SJ
Siyoon Jin
cs.CVcs.AI
On Valency
published · living versionsW_h2mepfcs·v1 · currentpublished
Repurposing Video Diffusion Transformers for Cross-View Temporal Object Correspondence
with Dahyun Chung, Honggyu An, Sangbeom Lim, Wonjin Nam +3
1 version
Preprints & journals
13 papers in the corpus · 2024–2026Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction2610.12299v1 · Dahyun Chung, Siyoon Jin, Hyunwook Choi et al.2026 · 0 citationsarXiv
World Observer: Joint Actor-Observer Generation for Persistent World Modeling2610.02162v1 · Hyunwook Choi, Dahyun Chung, Hyunsung Kim et al.2026 · 0 citationsarXiv
Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization2606.11180v1 · Paul Hyunbin Cho, Jinhyuk Jang, SeokYoung Lee et al.2026 · 0 citationsarXiv
WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation2603.16871v1 · Jisu Nam, Yicong Hong, Chun-Hao Paul Huang et al.2026 · 0 citationsarXiv
Grounding World Simulation Models in a Real-World Metropolis2603.15583v1 · Junyoung Seo, Hyunwook Choi, Minkyung Kwon et al.2026 · 0 citationsarXiv
CORAL: Correspondence Alignment for Improved Virtual Try-On2602.17636v1 · Jiyoung Kim, Youngjin Shin, Siyoon Jin 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
MATRIX: Mask Track Alignment for Interaction-aware Video Generation2510.07310v2 · Siyoon Jin, Seongchan Kim, Dahyun Chung et al.2025 · 0 citationsarXiv
Emergent Temporal Correspondences from Video Diffusion Transformers2506.17220v2 · Jisu Nam, Soowon Son, Dahyun Chung et al.2025 · 1 citationarXiv
Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry2506.13697v1 · Junyoung Seo, Jisang Han, Jaewoo Jung et al.2025 · 0 citationsarXiv
Appearance Matching Adapter for Exemplar-based Semantic Image Synthesis in-the-Wild2412.03150v2 · Siyoon Jin, Jisu Nam, Jiyoung Kim et al.2024 · 0 citationsarXiv
MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation2403.19144v1 · Seyeon Kim, Siyoon Jin, Jihye Park et al.2024 · 3 citationsarXiv
DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization2402.09812v2 · Jisu Nam, Heesu Kim, DongJae Lee et al.2024 · 25 citationsarXiv
Career total: 17 works. 13 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.