Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning Chenyu Y ang

Nov-15-2025, 06:32:18 GMT–Neural Information Processing Systems

Raw pixels are unstructured and often contain unnecessary and unpredictable details.

arxiv preprint arxiv, large language model, machine learning, (17 more...)

Neural Information Processing Systems

Nov-15-2025, 06:32:18 GMT

Conferences PDF

Country:
- Europe
  - Poland (0.04)
  - Netherlands > North Holland
    - Amsterdam (0.04)
- Asia > China
  - Shanghai > Shanghai (0.04)
  - Shaanxi Province > Xi'an (0.04)
  - Hong Kong (0.04)
  - Beijing > Beijing (0.04)

Genre:
- Research Report > Experimental Study (0.93)

Industry:
- Information Technology (0.46)

Technology:
- Information Technology
  - Sensing and Signal Processing > Image Processing (1.00)
  - Artificial Intelligence
    - Vision (1.00)
    - Natural Language
      - Large Language Model (1.00)
      - Chatbot (0.68)
    - Machine Learning > Neural Networks
      - Deep Learning (0.68)

Duplicate Docs Excel Report

Title
Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning Chenyu Y ang

Similar Docs Excel Report more

Title	Similarity	Source
None found