activity
20242026
collaborators

8 papers

cs.CV2026

Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulation

Songbur Wong, Xiaosong Jia, Junqi You +12

Evaluating end-to-end autonomous driving (E2E-AD) remains challenging, as existing driving simulation methods often trade off closed-loop interactivity (e.g., CARLA) and real-world…

cs.CV2026

LaGen: Towards Autoregressive LiDAR Scene Generation

Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang +7

Generative world models for autonomous driving (AD) are of great value in applications such as data augmentation, closed-loop simulation, and safety-critical scenario evaluation. U…

cs.CV2026

DriveVGGT: Calibration-Constrained Visual Geometry Transformers for Multi-Camera Autonomous Driving

Xiaosong Jia, Yanhao Liu, Yu Hong +5

Feed-forward reconstruction has been progressed rapidly, with the Visual Geometry Grounded Transformer (VGGT) being a notable baseline. However, directly applying VGGT to autonomou…

cs.CV2026

ReCoSplat: Autoregressive Feed-Forward Gaussian Splatting Using Render-and-Compare

Freeman Cheng, Botao Ye, Xueting Li +3

Online novel view synthesis remains challenging, requiring robust scene reconstruction from sequential, often unposed, observations. We present ReCoSplat, an autoregressive feed-fo…

cs.CV2026

Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention

Xiaosong Jia, Yihang Sun, Junqi You +5

Feedforward models for novel view synthesis (NVS) have recently advanced by transformer-based methods like LVSM, using attention among all input and target views. In this work, we…

cs.LG2025

DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving

Xiaosong Jia, Junqi You, Zhiyuan Zhang +1

End-to-end autonomous driving (E2E-AD) has emerged as a trend in the field of autonomous driving, promising a data-driven, scalable approach to system design. However, existing E2E…