Tianxing CHEN (陈天行)4th-year Undergraduate Student @ SZU
Computer Science and Technology,
CSSE, |
|
My research interests mainly focus on Embodied AI (具身智能), on behavior planning and policy based on Diffusion Model, LLM and Reinforcement Learning. I am very interested in the application of policy in robot manipulation and autonomous driving scenarios.
Feel free to contact me by email if you are interested in discussing or collaborating with me.
The University of Hong Kong (HKU), Hong Kong, China Incoming PhD. Student 25'Fall |
Shenzhen University (SZU), China B.Eng. (currently studying) in Computer Science and Technology (Excellent Class), CSSE
GPA 91.0 / 100, Excellent Star of SZU (荔园卓越之星, top 0.0067%)
Sep. 2021 - Jun. 2025 (expected) |
MMLab, The University of Hong Kong Feb. 2024 - Present, Member Supervised by Prof. Ping Luo |
OpenGVLab, Shanghai AI Laboratory (Pujiang National Laboratory) Feb. 2024 - Present, Intern Researcher, Shanghai, China Working with Prof. Jifeng Dai and Dr. Wenhai Wang |
Visual Computing Research Center (VCC) & National Engineering laboratory for Big Data System Computing Technology, Shenzhen University Sep. 2023 - Present, Intern Researcher, Shenzhen, China Supervised by Prof. Ruizhen Hu (国家优青), Dr. Jie Chen and Prof. Jianqiang Li (IET Fellow / 国家杰青) |
Under Review
|
G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation
Tianxing Chen*, Yao Mu*, Zhixuan Liang*, Zanxin Chen, Shijia Peng, Qiangyu Chen, Mingkun Xu, Ruizhen Hu, Hongyuan Zhang, Xuelong Li, Ping Luo†
Under Review 2024
Coming Soon
|
Under Review
|
RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins
Yao Mu*, Tianxing Chen*, Zanxin Chen*, Shijia Peng*, Zeyu Gao, Zhixuan Liang, Qiaojun Yu, Yude Zou, Mingkun Xu, Lunkai Lin, Zhiqiang Xie, Mingyu Ding and Ping Luo†
Under Review 2024
Coming Soon.
|
Under Review
|
Articulated Object Manipulation using Online Axis Estimation with SAM2-Based Tracking
Xi Wang*, Tianxing Chen*, Qiaojun Yu*, Tianling Xu, Zanxin Chen, Yiting Fu, Cewu Lu†, Yao Mu†, Ping Luo†
Under Review 2024
This study introduces a closed-loop pipeline that integrates interactive perception with online axis estimation from segmented 3D point clouds using Segment Anything Model 2 (SAM2), significantly enhancing the precision and efficiency of manipulating articulated objects, particularly in tasks requiring precise axis-based control.
|
ECCV WS (Best Paper)
|
RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)
Yao Mu*, Tianxing Chen*, Shijia Peng*, Zanxin Chen*, Zeyu Gao, Yude Zou, Lunkai Lin, Zhiqiang Xie and Ping Luo†
ECCV Workshop 2024 (Best Paper), MAAS
Using the COBOT Magic platform, we have collected diverse data on tool usage, human-robot interaction, and mobile manipulation. We present a cost-effective approach to creating digital twins using AI-generated content, transforming 2D images into detailed 3D models. Furthermore, we utilize large language models to generate expert-level training data and task-specific pose sequences oriented towards functionality.
|
Under Review
|
HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model
Mengkang Hu, Tianxing Chen, Qiguang Chen, Yao Mu, Wenqi Shaoz and Ping Luo†
Under Review 2024
This paper proposes HiAgent, a hierarchical framework that utilizes subgoals to manage the working memory of Large Language Model(LLM)-based agents.
HiAgent aims to address the poor performance of LLM-based agents when handling long-horizon tasks.
|
Under Review
|
ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation
Guanxing Lu*, Zifeng Gao*, Tianxing Chen, Wenxun Dai, Ziwei Wang, and Yansong Tang†
Under Review 2024
We propose a real-time point cloud-conditioned diffusion model named ManiCM for robotic manipulation that imposes the consistency constraint to the diffusion process, so that the model can generate robot actions in only one-step inference.
|
ICARM
|
Robust UAV Policy Learning for Urban Infrastructure Surface Screening
Bingging Du*, Uddin Md. Borhan*, Tianxing Chen, Jianyong Chen, Jiangiang Li†, and Jie Chen†
ICARM 2024, The IEEE International Conference on Advanced Robotics and Mechatronics
This paper presents a novel approach to enhance UAV policy learning for surface screening of urban infrastructure in environments lacking GPS.
|
(ACM-ICPC) International Collegiate Programming Contest Regional Contest.
Silver Medal 🥈, 银牌,(ACM-ICPC) 国际大学生程序设计竞赛亚洲区域赛 With Yuanjie He, Yifei Liu. Supervised by Prof. Jianbin Qin.
Team: SZU_Tencent
|
RoboCom Robot Development Competition (RAICOM)
National Runner-up 🏆, 全国亚军,睿抗机器人开发者大赛 With Weili Li, Jiaxuan Li. Supervised by Dr. Jie Chen.
|
[2024] National gold medal team & Provincial runner-up🏆, (CCCC) China Collegiate Computing Contest. |
[2023] Silver Medal🥈, (ACM-ICPC) International Collegiate Programming Contest Regional Contest (46th). |
[2023] National Runner-up🏆, RoboCom Robot Development Competition (RAICOM). |
[2023] Gold Medal, (GDCPC) China Collegiate Programming Contest Guangdong Provincial Contest. |
[2023] Silver Medal, (CCPC) China Collegiate Programming Contest National Invitational Contest. |
[2023] National First Prize, top 0.3%, LanQiao Cup Programming Contest (C/C++). |
[2023] National Silver Medal Team, (CCCC) China Collegiate Computing Contest. |
[2022] Provincial Second Prize, Wechat Mini Programs Application Development Contest. |
-- Selected -- | |
Best Paper Award at ECCV Workshop 2024 🏆
RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)
|
CCF Elite Collegiate Award, CCF优秀大学生 (2023) [Report]
- awarded by China Computer Federation (中国计算机学会)
- to the top 99 students nationwide |
Excellent Star of Shenzhen University, 荔园卓越之星 (2023) [Report]
- the highest honor for undergraduate students at Shenzhen University
- ranked 2nd among the 30,000 undergraduates in the school (top 0.0067%) - the only junior to win the award in 2023 - the only award-winning student of college in the past 3 years, CNY 50,000 |
AI4ProgrammingEdu (万木程林): Designer of ChatGLM AI teacher based on Zhipu AI open source model, developer of online hands-on teaching platform based on Scratch enlightenment programming game.
Outcome: Offline trial classes have been conducted in rural primary and secondary schools in Shanwei, Heyuan and other places.
|
Easy2Buy_Shouyi (易购首邑): Front-end design and development based on WeChat native framework, front-end and back-end interaction (JavaScript/wxml/wxss/json, Go).
Outcome: The demo has been delivered to Yangqu Government, Taiyuan City, Shanxi Province, and won the second prize (Provincial) in WeChat Mini Program Application Development Competition, [Report]
|