7 papers
GEM: Generative Supervision Helps Embodied Intelligence
Ruowen Zhao, Bangguo Li, Zuyan Liu +9
Embodied Vision-Language Models (VLMs) have demonstrated impressive performance and generalization in robotics, particularly within Vision-Language-Action frameworks. However, a si…
NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks
Junliang Ye, Shenghao Xie, Ruowen Zhao +5
3D object editing is essential for interactive content creation in gaming, animation, and robotics, yet current approaches remain inefficient, inconsistent, and often fail to prese…
ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding
Junliang Ye, Zhengyi Wang, Ruowen Zhao +2
Recently, the powerful text-to-image capabilities of ChatGPT-4o have led to growing appreciation for native multimodal large language models. However, its multimodal capabilities r…
Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization
Yikai Wang, Guangce Liu, Xinzhou Wang +5
The advancement of 4D (i.e., sequential 3D) generation opens up new possibilities for lifelike experiences in various applications, where users can explore dynamic objects or chara…
DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
Ruowen Zhao, Junliang Ye, Zhengyi Wang +4
Triangle meshes play a crucial role in 3D applications for efficient manipulation and rendering. While auto-regressive methods generate structured meshes by predicting discrete ver…
MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization
Yiwen Chen, Yikai Wang, Yihao Luo +5
Meshes are the de facto 3D representation in the industry but are labor-intensive to produce. Recently, a line of research has focused on autoregressively generating meshes. This a…