2 citations · 2 across the 7 of their papers we have counts for
5 papers · 1 filter
Can Video World Models Track Unobserved World States?
Joonghyuk Shin, Yicong Hong, Jaesik Park +1
Video world models are increasingly used as simulators, but visual fidelity alone does not show that a model maintains the hidden state of the world. We examine this difference wit…
Text-based Tactile Graphics Generation for the Visually Impaired
Ruihan Gao, Joonghyuk Shin, Ava Pun +3
Tactile graphics are a primary medium for blind and low-vision (BLV) individuals to access non-textual information. However, they are difficult to scale or personalize. While recen…
Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the Wild
Seunguk Do, Minwoo Huh, Joonghyuk Shin +1
Single-view 3D human reconstruction has achieved remarkable progress through the adoption of multi-view diffusion models, yet the recovered 3D humans often exhibit unnatural poses.…
SEAL-pose: Enhancing 3D Human Pose Estimation via a Learned Loss for Structural Consistency
Yeonsung Kim, Junggeun Do, Seunguk Do +3
3D human pose estimation (HPE) is characterized by intricate local and global dependencies among joints. Conventional supervised losses are limited in capturing these correlations…
Stabilizing Consistency Training: A Flow Map Analysis and Self-Distillation
Youngjoong Kim, Duhoe Kim, Woosung Kim +1
Consistency models have been proposed for fast generative modeling, achieving results competitive with diffusion and flow models. However, these methods exhibit inherent instabilit…