6 papers
ReMoT: Reinforcement Learning with Motion Contrast Triplets
Cong Wan, Zeyu Guo, Jiangyang Li +5
We present ReMoT, a unified training paradigm to systematically address the fundamental shortcomings of VLMs in spatio-temporal consistency -- a critical failure point in navigatio…
Persistent Autoregressive Mapping with Traffic Rules for Autonomous Driving
Shiyi Liang, Xinyuan Chang, Changjie Wu +8
Safe autonomous driving requires both accurate HD map construction and persistent awareness of traffic rules, even when their associated signs are no longer visible. However, exist…
FARTrack: Fast Autoregressive Visual Tracking with High Performance
Guijie Wang, Tong Lin, Yifan Bai +4
Inference speed and tracking performance are two critical evaluation metrics in the field of visual tracking. However, high-performance trackers often suffer from slow processing s…
FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving
Shuang Zeng, Xinyuan Chang, Mengwei Xie +6
Vision-Language-Action (VLA) models offer significant potential for end-to-end driving, yet their reasoning is often constrained by textual Chains-of-Thought (CoT). This symbolic c…
Grid: Omni Visual Generation
Cong Wan, Xiangyang Luo, Hao Luo +7
Visual generation has witnessed remarkable progress in single-image tasks, yet extending these capabilities to temporal sequences remains challenging. Current approaches either bui…
TACOcc:Target-Adaptive Cross-Modal Fusion with Volume Rendering for 3D Semantic Occupancy
Luyao Lei, Shuo Xu, Yifan Bai +1
The performance of multi-modal 3D occupancy prediction is limited by ineffective fusion, mainly due to geometry-semantics mismatch from fixed fusion strategies and surface detail l…