3 papers
cs.AI2026
World Models Need a Physical Registry: Learning Internal Predictive States for Physically Plausible World Models
Shinseong Kim, Jaeseok Jeong, Jianlong Fu +1
Video world models must generate physically plausible futures, not just realistic frames. Existing approaches typically use semantic, physical, or predictive information to guide t…
cs.CV2025
ASemConsist: Adaptive Semantic Feature Control for Training-Free Identity-Consistent Generation
Shin Seong Kim, Minjung Shin, Hyunin Cho +1
Recent text-to-image diffusion models have significantly improved visual quality and text alignment. However, generating a sequence of images while preserving consistent character…
cs.CV2025
TCFG: Tangential Damping Classifier-free Guidance
Mingi Kwon, Shin seong Kim, Jaeseok Jeong. Yi Ting Hsiao +1
Diffusion models have achieved remarkable success in text-to-image synthesis, largely attributed to the use of classifier-free guidance (CFG), which enables high-quality, condition…