Summary

Currently employed at HKUST(GZ). An MPhil student at HKUST(GZ). B.S. in Computer Science from Fudan University.

Education

• Artificial Intelligence
  HKUST(GZ)
• Computer Science

  2026-06
  Fudan University

  GPA: 3.73

Publications

• Paper Title Number 1

  2009
  Journal 1

  This paper is about the number 1. The number 2 is left for future work.

  View Publication
• Paper Title Number 2

  2010
  Journal 1

  This paper is about the number 2. The number 3 is left for future work.

  View Publication
• Paper Title Number 3

  2015
  Journal 1

  This paper is about the number 3. The number 4 is left for future work.

  View Publication
• Paper Title Number 4

  2024
  GitHub Journal of Bugs

  This paper is about fixing template issue #693.

  View Publication
• Paper Title Number 5, with math $$E=mc^2$$

  2024
  GitHub Journal of Bugs

  This paper is about a famous math equation, $$E=mc^2$$

  View Publication
• EmoVid: A Multimodal Emotion Video Dataset for Emotion-Centric Video Understanding and Generation

  2025
  AAAI 2026 (Oral)

  We introduce EmoVid, the first multimodal, emotion-annotated video dataset specifically designed for creative media. It enables emotion-conditioned video generation by fine-tuning the Wan2.1 model.

  View Publication
• EmoSpace: Fine-Grained Emotion Prototype Learning for Immersive Affective Content Generation

  2026
  arXiv preprint

  EmoSpace learns dynamic, interpretable emotion prototypes through vision-language alignment, enabling fine-grained emotional control for immersive VR content generation, including emotional image outpainting, stylized generation, and emotional panorama generation.

  View Publication
• Where a New Concept Must Enter: Entry Point Gates Cross-Task Usability in Unified Multimodal Models

  2026
  arXiv preprint

  We isolate generation-to-understanding and understanding-to-generation transfer in unified multimodal models by binding a novel visual concept through exactly one task direction, finding that cross-task usability is governed by where the binding enters the shared computation.

  View Publication
• InternLumina-U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding and Image Generation

  2026
  Technical report (in preparation)

  InternLumina-U2 is a unified diffusion large language model that shares a single MoE diffusion backbone with a multi-codebook visual tokenizer for text question answering, image understanding and editing, image generation, video understanding, and 3D understanding.

  View Publication

Presentations

• Talk 1 on Relevant Topic in Your Field

  2012
  UC San Francisco, Department of Testing

  San Francisco, CA, USA
• Tutorial 1 on Relevant Topic in Your Field

  2013
  UC-Berkeley Institute for Testing Science

  Berkeley, CA, USA
• Talk 2 on Relevant Topic in Your Field

  2014
  London School of Testing

  London, UK
• Conference Proceeding talk 3 on Relevant Topic in Your Field

  2014
  Testing Institute of America 2014 Annual Conference

  Los Angeles, CA, USA

Teaching

• Teaching experience 1

  2014
  University 1, Department

  Role: Undergraduate course
• Teaching experience 2

  2015
  University 1, Department

  Role: Workshop

Portfolio

• Portfolio item number 1
  Portfolio

  Short description of portfolio item number 1
  

  View Project