7 papers
FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
Xirui Li, Zhe Liu, Xiaoqing Ye +4
Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are confined to a fixed action voca…
FASTER: Rethinking Real-Time Flow VLAs
Yuxiang Lu, Zhe Liu, Xianzhe Fan +5
Real-time execution is crucial for deploying Vision-Language-Action (VLA) models in the physical world. Existing asynchronous inference methods primarily optimize trajectory smooth…
UniLION: Towards Unified Autonomous Driving Model with Linear Group RNNs
Zhe Liu, Jinghua Hou, Xiaoqing Ye +3
Although transformers have demonstrated remarkable capabilities across various domains, their quadratic attention mechanisms introduce significant computational overhead when proce…
HybridTM: Combining Transformer and Mamba for 3D Semantic Segmentation
Xinyu Wang, Jinghua Hou, Zhe Liu +1
Transformer-based methods have demonstrated remarkable capabilities in 3D semantic segmentation through their powerful attention mechanisms, but the quadratic complexity limits the…
LION: Linear Group RNN for 3D Object Detection in Point Clouds
Zhe Liu, Jinghua Hou, Xinyu Wang +4
The benefit of transformers in large-scale 3D point cloud perception tasks, such as 3D object detection, is limited by their quadratic computation cost when modeling long-range rel…
OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection
Jinghua Hou, Tong Wang, Xiaoqing Ye +6
Accurate depth information is crucial for enhancing the performance of multi-view 3D object detection. Despite the success of some existing multi-view 3D detectors utilizing pixel-…