InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion Paper โข 2512.17504 โข Published Dec 19, 2025 โข 97
Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation Paper โข 2512.17040 โข Published Dec 18, 2025 โข 28
EgoX: Egocentric Video Generation from a Single Exocentric Video Paper โข 2512.08269 โข Published Dec 9, 2025 โข 119
PHUMA: Physically-Grounded Humanoid Locomotion Dataset Paper โข 2510.26236 โข Published Oct 30, 2025 โข 30
ACG: Action Coherence Guidance for Flow-based VLA models Paper โข 2510.22201 โข Published Oct 25, 2025 โข 37
DesignLab: Designing Slides Through Iterative Detection and Correction Paper โข 2507.17202 โข Published Jul 23, 2025 โข 51
SphereDiff: Tuning-free Omnidirectional Panoramic Image and Video Generation via Spherical Latent Representation Paper โข 2504.14396 โข Published Apr 19, 2025 โข 27
TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models Paper โข 2407.09012 โข Published Jul 12, 2024 โข 10
TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models Paper โข 2407.09012 โข Published Jul 12, 2024 โข 10