6 papers
DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving
Xiaolu Liu, Yicong Li, Song Wang +3
Recently, world models have been incorporated into the autonomous driving systems to improve the planning reliability. Existing approaches typically predict future states through a…
VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration
Hanxun Yu, Wentong Li, Xuan Qu +3
Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based scenarios. Existing to…
A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding
Zhan Shi, Song Wang, Junbo Chen +1
Visual grounding aims to identify objects or regions in a scene based on natural language descriptions, essential for spatially aware perception in autonomous driving. However, exi…
MambaMap: Online Vectorized HD Map Construction using State Space Model
Ruizi Yang, Xiaolu Liu, Junbo Chen +1
High-definition (HD) maps are essential for autonomous driving, as they provide precise road information for downstream tasks. Recent advances highlight the potential of temporal m…
Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning
Hanxun Yu, Wentong Li, Song Wang +2
Despite encouraging progress in 3D scene understanding, it remains challenging to develop an effective Large Multi-modal Model (LMM) that is capable of understanding and reasoning…
Uncertainty-Instructed Structure Injection for Generalizable HD Map Construction
Xiaolu Liu, Ruizi Yang, Song Wang +3
Reliable high-definition (HD) map construction is crucial for the driving safety of autonomous vehicles. Although recent studies demonstrate improved performance, their generalizat…