GitHub

Hi there 👋

🤗 Hello! I am Yingqing He. Nice to meet you!
👨‍💻‍ I am a Ph.D. student at HKUST, supervised by Professor Qifeng Chen.
👨‍💻‍ My research focuses on generative AI, in particular, text-to-video generation, controllable visual generation, and multimodal generation.
📫 How to reach me: yhebm@connect.ust.hk
📣 Our lab is hiring engineering-oriented research assistants (RA). If you would like to apply, feel free to reach out with your CV!

More recent projects:

  • Code [2024-12-24] VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE. (State-of-the-art Video VAE models).

  • Code [CVPR 2024] Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners.

  • Code [ECCV 2024] Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation.

Awesome series:

For more of my generative AI projects, please check my personal webpage.

Pinned Loading

  1. Let's finetune video generation models!

    Python 553 30

  2. 🔥🔥🔥 A curated list of papers on LLMs-based multimodal generation (image, video, 3D and audio).

    HTML 552 31

  3. LVDM: Latent Video Diffusion Models for High-Fidelity Long Video Generation

    Python 503 23

  4. VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

    Python 5.1k 413

  5. [ICLR 2024 Spotlight] Official implementation of ScaleCrafter for higher-resolution visual generation at inference time.

    Python 507 28

  6. [AAAI 2024] Follow-Your-Pose: This repo is the official implementation of "Follow-Your-Pose : Pose-Guided Text-to-Video Generation using Pose-Free Videos"

    Python 1.4k 96

Read the original on github.com ↗