4 papers · 1 filter
EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields
Zhaoyang Yang, Yurun Jin, Lizhe Qi +2
Pretrained video diffusion models provide powerful spatiotemporal generative priors, making them a natural foundation for robotic world models. While recent world-action models joi…
DanceCrafter: Fine-Grained Text-Driven Controllable Dance Generation via Choreographic Syntax
Hang Yuan, Xiaolin Hu, Yan Wan +8
Text-driven controllable dance generation remains under-explored, primarily due to the severe scarcity of high-quality datasets and the inherent difficulty of articulating complex…
ScalSelect: Scalable Training-Free Multimodal Data Selection for Efficient Visual Instruction Tuning
Changti Wu, Jiahuai Mao, Yuzhuo Miao +6
Large-scale Visual Instruction Tuning (VIT) has become a key paradigm for advancing the performance of vision-language models (VLMs) across various multimodal tasks. However, train…
Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks
Shijie Lian, Changti Wu, Laurence Tianruo Yang +4
Spatial intelligence spans a rich suite of abilities, including visualising and transforming shapes, mentally rotating objects, judging relational positions and containment, and es…