6 papers
TopoDiT-3D: Topology-Aware Diffusion Transformer with Bottleneck Structure for 3D Point Cloud Generation
Zechao Guan, Feng Yan, Shuai Du +2
Recent advancements in Diffusion Transformer (DiT) models have significantly improved 3D point cloud generation. However, existing methods primarily focus on local feature extracti…
InstructVEdit: A Holistic Approach for Instructional Video Editing
Chi Zhang, Chengjian Feng, Feng Yan +5
Video editing according to instructions is a highly challenging task due to the difficulty in collecting large-scale, high-quality edited video pair data. This scarcity not only li…
Boosting Robotic Manipulation Generalization with Minimal Costly Data
Liming Zheng, Feng Yan, Fanfan Liu +3
The growing adoption of Vision-Language-Action (VLA) models in embodied AI intensifies the demand for diverse manipulation demonstrations. However, high costs associated with data…
RoboTron-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction
Yufeng Zhong, Chengjian Feng, Feng Yan +3
In language-guided visual navigation, agents locate target objects in unseen environments using natural language instructions. For reliable navigation in unfamiliar scenes, agents…
RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous Driving
Zhijian Huang, Chengjian Feng, Feng Yan +5
Large Multimodal Models (LMMs) have demonstrated exceptional comprehension and interpretation capabilities in Autonomous Driving (AD) by incorporating large language models. Despit…
RoboTron-Mani: All-in-One Multimodal Large Model for Robotic Manipulation
Feng Yan, Fanfan Liu, Liming Zheng +5
Recently, robotics has advanced significantly through the integration of larger models and large-scale datasets. However, challenges remain in applying these models to 3D spatial i…