Yuchen Xie (Ares)

I am a third-year undergraduate student at Nanyang Technological University (NTU), Singapore. My research interests lie in Generative AI, with applications in world models and robotics. I am currently doing research on 3D/world models at the Spatial Intelligence Lab, advised by Prof. Jiawang Bian. I am also an algorithm engineer intern at ByteDance, working on AIGC, and a Research Consultant at WorldQuant.

I am grateful to have worked closely with and received extensive help from Prof. Weisi Lin, Prof. Jianfei Yang, Dr. Donny Y. Chen, Dr. Xinyu Zhou, Weijie Wang, Xin Li and Annan Wang.

I'm always glad to talk about research or collaboration—just email me at XIEY0038@e.ntu.edu.sg.

Email  /  Google Scholar  /  LinkedIn

Yuchen Xie (Ares)
News
  • [2026/11] Our paper AllocFlow on end-to-end portfolio trading with flow matching is released.
  • [2026/11] 💼 I joined WorldQuant as a Research Consultant.
  • [2026/10] 🥇 Reached Gold Level in the WorldQuant Challenge!
  • [2026/09] Our paper DN-MOPD on multi-teacher on-policy distillation is released.
  • [2026/09] 🏅 I was placed on the Dean's List (Top 5%) in AY 2025-2026.
  • [2026/06] Our paper USS on unified spatial-semantic prompting for embodied visual tracking is released.
  • [2026/06] 🏆 Won First Place in the ICME 2026 Grand Challenge: Physics-Grounded Stress Testing of World Models!
  • [2026/04] 💼 I joined ByteDance as an algorithm engineer intern, working on AIGC.
  • [2025/05] 💼 I joined Whale Cloud as a computer vision algorithm engineer intern.
Publications

* Equal contribution  /  † Corresponding author

AllocFlow overview AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data
Annan Wang*, Yuchen Xie*, Yu Cen, Leon Liangyu Chen, Qianyu Julie Zhu, Xin Li, Tianyi Wei, Weisi Lin†
Paper / Project

AllocFlow reads the raw price history of every asset and generates the whole long/short portfolio at once with a cross-asset flow Transformer, trained by imitation and then group-relative RL. After fees it reaches a Calmar ratio of 4.04 on 14 unseen months of crypto futures, and 4.90 on six more months without retraining.

USS method USS: Unifying Spatial-Semantic Prompting for End to End Embodied Visual Tracking
Yuchen Xie*, Xinyu Zhou*, Kuangji Zuo, Yanshuo Lu, Fengrui Huang, Boyu Ma, Jianfei Yang†
Paper / Project

USS lets a robot follow a target specified by text, a point, a box or a mask, mapping any of these prompts to egocentric waypoints end to end. Policies trained only in simulation transfer zero-shot to a real humanoid robot across 320 real-world trials.

DN-MOPD overview Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation
Xin Li, Hao Jiang, Xin Gao, Annan Wang, Yuchen Xie, Jinghao Guo, Xingwei Qu, Yichi Zhang, Chau Yuen
Paper / Project

DN-MOPD keeps label routing in multi-teacher on-policy distillation but rescales each domain's teacher feedback by its measured spread, so that no single domain dominates the shared student.

Experience
WorldQuant
2026.11 - Present
Research Consultant
ByteDance
2026.04 - Present
Algorithm Engineer Intern, AIGC
Whale Cloud
2025.05 - 2025.08
Computer Vision Algorithm Engineer Intern
Nanyang Technological University
2024.08 - Present
Undergraduate Researcher at Spatial Intelligence Lab, advised by Prof. Jiawang Bian
Undergraduate Researcher at MARS Lab, advised by Prof. Jianfei Yang
Honors and Awards

This template is a modification to Jon Barron's website.