Hi, I’m Tian Xia, a master’s student in CSE at Harvard University, working with Prof. Qianqian Wang. Previously, I graduated from the University of Michigan, Ann Arbor, with majors in Honors Math, Honors CS, and DS, where I worked with Prof. Joyce Chai at the SLED Lab. Outside of research, I enjoy skiing, karting, and flying to different cities to explore.

Research

My research interests focus on 3D understanding, generative AI, and embodied agents, emphasizing scalable systems and cross-modal representations. I aim to develop machine learning systems that integrate vision, language, and spatial information to understand and model the physical world, enabling self-evolving agents to improve through interaction and feedback.

Over time, my interests have expanded to encompass a broader range of topics, including computer vision, multimodal learning, and robotics. My current focus areas include:

Visual and spatial understanding: 3D reconstruction, recognition, and motion understanding.
Generative modeling: Video generation and cross-modal synthesis.
Multimodal and self-evolving agents: Multimodal reasoning and strategy refinement through feedback.

Publications

NeurIPS 2026 (Spotlight)

MoSE3 Figure 1: dense SE(3) predictions for rigid, articulated, and non-rigid motion

MoSE3: Learning World-Space SE(3) at Every Pixel

Jiahuan Cheng*, Zhiyi Li*, Tian Xia*, Ruojin Cai, Yilun Du, Qianqian Wang

[Project][Paper]

arXiv 2026

Ranking-PE overview of multimodal clinical diagnosis and ranking-aware evaluation

Ranking-PE: Ranking-Aware Prompt Optimization for Multimodal Clinical Diagnosis

Tian Xia, Minghao Liu, Yiqing Liang, Laixi Shi, Jiayun Wang

[Project][Arxiv][Paper]

3D-LLM/VLA @ CVPR 2025

SAB3R: Semantic-Augmented Backbone in 3D Reconstruction

Xuweiyi Chen*, Tian Xia*, Sihan XU, Jianing Yang, Joyce Chai, Zezhou Cheng

[Project][Arxiv][Code][Poster]

TMLR 2024

UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control

Tian Xia*, Xuweiyi Chen*, Sihan Xu

[Project][Arxiv][Code]

Honors and Awards

2025: Outstanding Achievement in Mathematics Awards
2024: Evelyn O. Bychinsky Awards
2024: James B. Angell Scholar
2023, 2024: M.S. Keeler Department of Mathematics Merit Scholarships
2022, 2023: University Honors

Educations

2025.08 - now, S.M. in Computational Science and Engineering, Harvard University
2022.09 - 2025.05, B.S. in Honors Mathematics, Honors Computer Science and Data Science, University of Michigan, Ann Arbor