Seungryong Kim
10 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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 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.
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.
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.
This paper presents Lip Forcing, an autoregressive diffusion method for real-time video-to-video lip synchronization.
This paper proposes SpatialClaw, a training-free framework for spatial reasoning that enables open-ended, complex 3D/4D spatial reasoning.
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.
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.
The paper presents a new framework for video matting that improves consistency across chunk boundaries in long videos.
This paper introduces ThinkWorld, a VLA learning framework that grounds action reasoning in world dynamics and strengthens it through reinforcement learning with world imagination.
Papers
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.