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

I am a second year CS PhD student at Shanghai Jiao Tong University, adviced by Prof. Junchi Yan. I am also a research intern at Shanghai AI Lab under the supervision of Dr. Hongyang Li.

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 from SJTU, Dr. Da Zheng and Prof. Zheng Zhang from Amazon, Dr. Wei Zhan , Dr. Liting Sun , and Prof. Masayoshi Tomizuka from UC Berkeley, Prof. Hang Zhao from Tsinghua University

Email  /  Google Scholar  /  Github

profile photo

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.
If you are interested in collaboration or internship for those topics, please feel free to drop me a email.

Selected Publication & Project
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
Tech Report, 2022

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

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.

PontTuset SentiMem: Attentive Memory Networks for Sentiment Classification in User Review
Xiaosong Jia , Qitian Wu, Xiaofeng Gao, Guihai Chen

Long-short memory mechanism to model users' dynamic mood and hobbies for sentiment classification

PontTuset Using Survival Theory in Early Pattern Detection for Viral Cascades
Xiaofeng Gao, Xiaosong Jia , Chaoqi Yang, Guihai Chen
TKDE, 2020

Applying survival theory for popular tweets prediction.

This website's source code is from Jon Barron