Xiaosong Jia (贾萧松)
jiaxiaosong1997 [At] gmail [dot] com

I am a third year CS PhD student (Wu Honor Class) at Shanghai Jiao Tong University, adviced by Prof. Junchi Yan.

Previously, I received my B.Eng in Computer Science from Zhiyuan Honor Class, Shanghai Jiao Tong University. I have the fortune to work with (chronological order): Prof. Xiaofeng Gao at SJTU, Dr. Da Zheng and Prof. Zheng Zhang at Amazon, Dr. Wei Zhan , Dr. Liting Sun , and Prof. Masayoshi Tomizuka at UC Berkeley, Prof. Hang Zhao at Tsinghua University, Prof. Hongyang Li at Shanghai AI Lab, Dr. Shaoshuai Shi at MPI-INF.

Email  /  Google Scholar  /  Github

profile photo
Research

I am interestied in machine learning and autonomous driving. Currently, I am focusing on the trajectory prediction, reinforcement learning, and end-to-end autonomous driving.

Selected Publications & Projects

* denotes Co-First Authors

PontTuset FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving
Yutao Zhu*, Xiaosong Jia*, Xinyu Yang, Junchi Yan
arXiv, 2024

Transformer based Fusion with 73.7 NDS + 10.1 FPS in nuScenes val set.

PontTuset Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving
Xiaosong Jia*, Zhenjie Yang*, Qifeng Li*, Zhiyuan Zhang*, Junchi Yan
arXiv, 2024

First benchmark for multi-ability end-to-end autonomous driving.

PontTuset AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving
Xiaosong Jia, Shaoshuai Shi, Zijun Chen, Li Jiang, Wenlong Liao, Tao He, Junchi Yan
arXiv, 2024

GPT-style Motion Prediction. State-of-the-art performance on Waymo Motion.

PontTuset Think2Drive: Efficient Reinforcement Learning by Thinking in Latent World Model for Quasi-Realistic Autonomous Driving (in CARLA-v2)
Qifeng Li*, Xiaosong Jia*, Shaobo Wang, Junchi Yan
ECCV, 2024

World model based reinforcement learning for autonomous driving. The first & only learning-based model could solve 39 complex scenearios in CARLA Leaderboard 2.0.

PontTuset ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving
Han Lu*, Xiaosong Jia*, Yichen Xie, Wenlong Liao, Xiaokang Yang, Junchi Yan
arXiv, 2024

Planning-oriented data selection for end-to-end autonomous driving. Training with 30% data beats full data.

PontTuset LLM4Drive: A Survey of Large Language Models for Autonomous Driving
Zhenjie Yang*, Xiaosong Jia*, Hongyang Li, Junchi Yan
arXiv, 2023

The first survey of LLM for autonomous driving. 800+ stars. Continuous updating.

PontTuset DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving
Xiaosong Jia, Yulu Gao, Li Chen, Junchi Yan, Patrick Langechuan Liu, Hongyang Li
ICCV, 2023 (Oral Presentation)

New paradigm for end-to-end autonomous driving without causal confusion.

PontTuset Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving
Xiaosong Jia, Penghao Wu, Li Chen, Jiangwei Xie, Conghui He, Junchi Yan, Hongyang Li
CVPR, 2023

BEV-based scalable end-to-end autonomous drving model.

PontTuset Planning-oriented Autonomous Driving
Yihan Hu*, Jiazhi Yang*, Li Chen*, Keyu Li*, Chonghao Sima, Xizhou Zhu, Siqi Chai, Senyao Du, Tianwei Lin, Wenhai Wang, Lewei Lu, Xiaosong Jia, Qiang Liu, Jifeng Dai, Yu Qiao, Hongyang Li
CVPR, 2023 (Best Paper Award)

All modules in one Transformer-based end-to-end network for autonomous driving.

PontTuset HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding
Xiaosong Jia , Penghao Wu, Li Chen, Hongyang Li, Yu Liu, Junchi Yan
TPAMI, 2023

Unified heterogeneous graph neural network for driving scene encoding. SOTA methods on INTERACTION and Waymo challenge.

PontTuset PPGeo: Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling
Penghao Wu, Li Chen, Hongyang Li, Xiaosong Jia, Junchi Yan, Yu Qiao
ICLR, 2023

Self-supervised pretraining for policy learning

PontTuset TCP: Trajectory-guided Control Prediction for Autonomous Driving
Penghao Wu*, Xiaosong Jia* , Li Chen*, Junchi Yan, Hongyang Li, Yu Qiao
NeurIPS, 2022

Trajectory-guided control paradigm for end-to-end autonomous driving. 1st method on Carla Leaderboard, with only a monocular camera, outperforming other methods with multiple cameras and LiDAR by a large margin.

PontTuset Towards Capturing the Temporal Dynamics for Trajectory Prediction: a Coarse-to-Fine Approach
Xiaosong Jia , Li Chen, Penghao Wu, Jia Zeng, Junchi Yan, Hongyang Li, Yu Qiao
CoRL, 2022

A plug-and-play module for trajectory prediction by enhancing the temporal correlation among the predicted time-steps.

PontTuset Multi-Agent Trajectory Prediction by Combining Egocentric and Allocentric Views
Xiaosong Jia , Liting Sun, Hang Zhao, Masayoshi Tomizuka, Wei Zhan
CoRL, 2021
ICCV Mair2 Workshop, 2021 (Best Student Paper Award)

Rethink the invariance property of the coordinate reprentation for trajectory prediction.

PontTuset INTERPRET: INTERACTION-Dataset-Based PREdicTion Challenge
Wei Zhan, Liting Sun, Hengbo Ma, Chenran Li, Xiaosong Jia, Masayoshi Tomizuka

Co-organized the competition in ICCV 2021. I was responsible for the design and implementation of the Joint Prediction and Conditional Prediction Tracks.

PontTuset IDE-Net: Interactive Driving Event and Pattern Extraction from Human Data
Xiaosong Jia , Liting Sun, Masayoshi Tomizuka, Wei Zhan
RA Letters, 2021
ICRA, 2021

Unsupervisedly extracting interactive behaviors in a whether, when, and what hierarchy.


This website's source code is from Jon Barron