2 citations · 4 across the 5 of their papers we have counts for
6 papers
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
Kaijin Chen, Dingkang Liang, Xin Zhou +4
Video world models have shown immense potential in simulating the physical world, yet existing memory mechanisms primarily treat environments as static canvases. When dynamic subje…
CharacterShot: Controllable and Consistent 4D Character Animation
Junyao Gao, Jiaxing Li, Wenran Liu +5
In this paper, we propose \textbf{CharacterShot}, a controllable and consistent 4D character animation framework that enables any individual designer to create dynamic 3D character…
FaceShot: Bring Any Character into Life
Junyao Gao, Yanan Sun, Fei Shen +4
In this paper, we present FaceShot, a novel training-free portrait animation framework designed to bring any character into life from any driven video without fine-tuning or retrai…
LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?
Kexian Tang, Junyao Gao, Yanhong Zeng +6
Many real-world applications of spatial intelligence, such as robotic control, autonomous driving, and automated assembly, require spatial reasoning across multiple sequential step…
AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation
Yanan Sun, Yanchen Liu, Yinhao Tang +2
The field of text-to-image (T2I) generation has made significant progress in recent years, largely driven by advancements in diffusion models. Linguistic control enables effective…
StyleShot: A Snapshot on Any Style
Junyao Gao, Yanchen Liu, Yanan Sun +4
In this paper, we show that, a good style representation is crucial and sufficient for generalized style transfer without test-time tuning. We achieve this through constructing a s…