1.1

Xiangnan Wu

吴祥楠 Multimodal Understanding & Embodied Intelligence

Building generalist intelligent agents that perceive, reason, and act across both physical and virtual worlds.

I am a Ph.D. candidate at UCAS & NLPR@CASIA, advised by Yan Huang and Liang Wang.

My research centers on Embodied Intelligence (Robotics & Game Agents) and Multimodal Models. My long-term goal is to develop generalist intelligent agents that assist people across both physical and virtual worlds, currently focusing on VLM as Policy and World Models.

2.1

Research Focus

I. Multimodal Understanding 2.1

Encoding linguistic semantics and visual signals within a shared latent space, enabling neural networks to comprehend the physical world across both spatial and temporal dimensions.

II. Embodied Intelligence 2.2

Leveraging upstream multimodal understanding to empower embodied agents—translating rich perceptual representations into world modeling, reasoning, and closed-loop action policies across physical robots and virtual environments.

3.1

Publications & Systems

I. Conference Papers 3.1

II. Preprints & Technical Reports 3.2

III. Open-Source Systems & Benchmarks 3.3

4.1

Recent News

IV. Dispatches & Milestones 4.1

  • We open-sourced NextTransformer, a compute-matched benchmark and autonomous research arena for next-generation Transformer architectures (Observatory).

    2026.11
  • Released two new preprints on embodied foundation agents: Scaling in Games and OneWM.

    2026.10
  • Video-Arena, our benchmark for spatiotemporal world state understanding and tracking, is now available on arXiv.

    2026.10
  • Concluded my research internship at Agibot Research.

    2026.08
  • EgoDemoGen is accepted to ACM MM 2026.

    2026.07
  • E-TTS is accepted to ECCV 2026.

    2026.06
  • BridgeVLA is accepted to NeurIPS 2025.

    2025.11

5.1

Experience

V. Research Appointments 5.1

Agibot Research

· Research Intern
2026.02 – 2026.08

Vision-Language-Action model pretrain.

Microsoft Research Asia

· Research Intern, Visual Computing Group
2025.11 – 2026.02

Multimodal Agent research in the Visual Computing Group.

6.1

Honors & Awards

VI. Selected Distinctions 6.1

  • National Scholarship Ministry of Education, China
    2025
  • National Scholarship Ministry of Education, China
    2024
  • Beijing “San Hao” Student Beijing Municipal Education Commission
    2024
  • National Undergraduate Electronic Design Contest (Second Prize) National Competition
    2024
  • National Undergraduate Mathematical Contest in Modeling (Second Prize) National Competition
    2024

Table of Contents

Figure Preview