Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Seungryong Kim

Seungryong Kim

10 indexed papers

Recent (6 mo)
10
With code
0
Influential cites
0
Benchmarked
0

Publications per year

10
26

Top categories

Vision×10AI×3Robotics×2ML×2Numerical Analysis×1

Frequent co-authors

Jaeyeong Kim4×
Min-Hung Chen2×
Yu-Chiang Frank Wang2×
Ines Kim2×
Jahyeok Koo2×
Minkyung Kwon2×

Research Timeline

2026
MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents

MORPHOS is a novel autoregressive framework that generates dynamic 3D assets (like meshes and radiance fields) from videos by using a unified 4D representation to ensure temporal consistency and handle changing object topologies.

MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents

MORPHOS is a novel autoregressive framework that generates dynamic 3D assets (like meshes and radiance fields) from videos by using a unified 4D representation to ensure temporal consistency and handle changing object topologies.

Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text

T2Mo is a novel framework that generates controllable dynamic 3D object shapes by combining explicit 3D trajectories for spatial guidance with natural language text semantics.

Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text

T2Mo is a novel framework that generates controllable dynamic 3D object shapes by combining explicit 3D trajectories for spatial guidance with natural language text semantics.

Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization

This paper presents Lip Forcing, an autoregressive diffusion method for real-time video-to-video lip synchronization.

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

This paper proposes SpatialClaw, a training-free framework for spatial reasoning that enables open-ended, complex 3D/4D spatial reasoning.

Geometric Action Model for Robot Policy Learning

The paper proposes the Geometric Action Model (GAM), a language-conditioned manipulation policy that uses a pretrained geometric foundation model to reason about 3D geometry and perform contact-rich manipulation.

Error-Conditioned Neural Solvers

This paper proposes Error-conditioned Neural Solvers (ENS) for neural surrogate models to iteratively correct predictions by using the PDE residual field as input, achieving higher accuracy than optimization-based methods.

VideoMaMa++: Temporally Consistent Video Matting via Preserve-and-Refine Token

The paper presents a new framework for video matting that improves consistency across chunk boundaries in long videos.

ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning

This paper introduces ThinkWorld, a VLA learning framework that grounds action reasoning in world dynamics and strengthens it through reinforcement learning with world imagination.

Highlighted terms show continued research focus across papers

Papers

cs.ROcs.AIcs.CVEmpiricalRecentOct 27, 2026

ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning

Chaehyun Kim, Chi-Pin Huang, Jisoo Kim, Min-Hung Chen +3 more

This paper introduces ThinkWorld, a VLA learning framework that grounds action reasoning in world dynamics and strengthens it through reinforcement learning with world imagination.

View →
cs.CVEmpirical
Recent
Oct 19, 2026

VideoMaMa++: Temporally Consistent Video Matting via Preserve-and-Refine Token

Sangbeom Lim, Seoung Wug Oh, Heeji Yoon, Seungryong Kim +1 more

The paper presents a new framework for video matting that improves consistency across chunk boundaries in long videos.

View →
cs.LGcs.AIcs.CVEmpiricalRecentJun 25, 2026

Error-Conditioned Neural Solvers

Haina Jiang, Liam Wang, Peng-Chen Chen, Min Seop Kwak +3 more

This paper proposes Error-conditioned Neural Solvers (ENS) for neural surrogate models to iteratively correct predictions by using the PDE residual field as input, achieving higher accuracy than optim…

View →
cs.ROcs.CVcs.LGEmpiricalRecentJun 15, 2026

Geometric Action Model for Robot Policy Learning

Jisang Han, Seonghu Jeon, Jaewoo Jung, René Zurbrügg +6 more

The paper proposes the Geometric Action Model (GAM), a language-conditioned manipulation policy that uses a pretrained geometric foundation model to reason about 3D geometry and perform contact-rich m…

View →
cs.CVcs.AIEmpiricalRecentJun 11, 2026

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Seokju Cho, Ryo Hachiuma, Abhishek Badki, Hang Su +7 more

This paper proposes SpatialClaw, a training-free framework for spatial reasoning that enables open-ended, complex 3D/4D spatial reasoning.

View →
cs.CVEmpiricalRecentJun 9, 2026

Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization

Paul Hyunbin Cho, Jinhyuk Jang, SeokYoung Lee, Joungbin Lee +6 more

This paper presents Lip Forcing, an autoregressive diffusion method for real-time video-to-video lip synchronization.

View →
cs.CVRecentJun 3, 2026

Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text

Jaeyeong Kim, Ines Kim, Jahyeok Koo, Seungryong Kim

T2Mo is a novel framework that generates controllable dynamic 3D object shapes by combining explicit 3D trajectories for spatial guidance with natural language text semantics.

View →
cs.CVRecentJun 3, 2026

Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text

Jaeyeong Kim, Ines Kim, Jahyeok Koo, Seungryong Kim

T2Mo is a novel framework that generates controllable dynamic 3D object shapes by combining explicit 3D trajectories for spatial guidance with natural language text semantics.

View →
cs.CVRecentJun 1, 2026

MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents

Minkyung Kwon, Jinhyeok Choi, Youngjin Shin, Jaeyeong Kim +2 more

MORPHOS is a novel autoregressive framework that generates dynamic 3D assets (like meshes and radiance fields) from videos by using a unified 4D representation to ensure temporal consistency and handl…

View →
cs.CVRecentJun 1, 2026

MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents

Minkyung Kwon, Jinhyeok Choi, Youngjin Shin, Jaeyeong Kim +2 more

MORPHOS is a novel autoregressive framework that generates dynamic 3D assets (like meshes and radiance fields) from videos by using a unified 4D representation to ensure temporal consistency and handl…

View →