7 papers
Beyond Text Conditioning: A Systematic Study of MLLM-DiT Fusion for Video Generation
Yanbo Ding, Yijia Fan, Caihua Shan +8
Diffusion Transformers (DiTs) have become the dominant paradigm for high-fidelity video generation, yet their ability to perform high-level semantic planning remains limited. While…
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
Yifan Zhou, Qihao Yang, Yan Li +14
Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benc…
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
Weijie Wang, Xiaoxuan He, Youping Gu +9
Recent video foundation models demonstrate impressive visual synthesis but frequently suffer from geometric inconsistencies. While existing methods attempt to inject 3D priors via…
DepthArb: Training-Free Depth-Arbitrated Generation for Occlusion-Robust Image Synthesis
Hongjin Niu, Jiahao Wang, Xirui Hu +4
Text-to-image models often struggle to synthesize correct occlusion relationships among multiple objects, especially in densely overlapping regions. Many training-free layout-guide…
MotionWeaver: Holistic 4D-Anchored Framework for Multi-Humanoid Image Animation
Xirui Hu, Yanbo Ding, Jiahao Wang +4
Character image animation, which synthesizes videos of reference characters driven by pose sequences, has advanced rapidly but remains largely limited to single-human settings. Exi…
MTVCraft: Tokenizing 4D Motion for Arbitrary Character Animation
Yanbo Ding, Xirui Hu, Zhizhi Guo +6
Character image animation has rapidly advanced with the rise of digital humans. However, existing methods rely largely on 2D-rendered pose images for motion guidance, which limits…
DynamicID: Zero-Shot Multi-ID Image Personalization with Flexible Facial Editability
Xirui Hu, Jiahao Wang, Hao Chen +4
Recent advances in text-to-image generation have driven interest in generating personalized human images that depict specific identities from reference images. Although existing me…