This internship is in ITRI's Information and Communications Research Laboratories (ICL).

Job Description:
1. Participate in practical projects involving multimodal large language models (LLMs) for image and text processing.
2. Develop models for image recognition and generation technologies, integrating visual information and textual descriptions for semantic understanding, and apply them to multimodal content generation.
3. Conduct surveys and report on related research papers and technologies.

Qualifications：
1. Master's student in Computer Science, Information Systems, or related fields.
2. Experience in researching or working with generative learning models (e.g., GPT, Llama, Mistral, InternVL).
3. Knowledge of image processing, machine learning, and deep learning analysis techniques.
4. Proficient in Linux system operations and Python development.