6 papers
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…
Spatial Retrieval Augmented Autonomous Driving
Xiaosong Jia, Chenhe Zhang, Yule Jiang +8
Existing autonomous driving systems rely on onboard sensors (cameras, LiDAR, IMU, etc) for environmental perception. However, this paradigm is limited by the drive-time perception…
TrajTok: Technical Report for 2025 Waymo Open Sim Agents Challenge
Zhiyuan Zhang, Xiaosong Jia, Guanyu Chen +2
In this technical report, we introduce TrajTok, a trajectory tokenizer for discrete next-token-prediction based behavior generation models, which combines data-driven and rule-base…
Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)
Zhenjie Yang, Xiaosong Jia, Qifeng Li +3
Reinforcement Learning (RL) can mitigate the causal confusion and distribution shift inherent to imitation learning (IL). However, applying RL to end-to-end autonomous driving (E2E…
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…
Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model
Junqi You, Xiaosong Jia, Zhiyuan Zhang +2
For end-to-end autonomous driving (E2E-AD), the evaluation system remains an open problem. Existing closed-loop evaluation protocols usually rely on simulators like CARLA being les…