Thanks to visit codestin.com
Credit goes to github.com

Skip to content
View patrickamadeus's full-sized avatar
โšก
โšก

Block or report patrickamadeus

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
patrickamadeus/README.md

๐Ÿ‘‹ Hi, I'm Patrick

๐ŸŽ“ I'm a Research Engineer at SMU ๐Ÿ‡ธ๐Ÿ‡ฌ, advised by Prof. Chong-Wah Ngo, working on the intersection of multimodal and multilingual learning.
๐Ÿ”œ I will be pursuing PhD, focusing on vision-language representation learning and reasoning architectures (excl. future interests).

๐Ÿ’ก Up until now, my research interests include:

  • ๐Ÿค– Multimodal Learning: VLMs, alignment, efficient architectures, and multimodal RAG.
  • ๐ŸŒ Multilingual Alignment: Low-resource language transfer and domain-specific benchmarking.
  • ๐Ÿง  Reasoning Architectures: Efficient decoding, hallucination mitigation, and model interpretability.

๐Ÿงช Previously, I earned my CS degree at ITB ๐Ÿ‡ฎ๐Ÿ‡ฉ under Prof. Ayu Purwarianti, working on explainable synthetic data generation.
๐Ÿ› ๏ธ I also enjoy building applied AI systemsโ€”check out some of my work below!


๐Ÿ“ฌ Email me โ€ข ๐ŸŒ Website โ€ข ๐Ÿ“ Google Scholar โ€ข ๐Ÿ’ผ LinkedIn

Pinned Loading

  1. vqa-nle-llava vqa-nle-llava Public

    Novel approach that leverages LVLMs to efficiently generate high-quality synthetic VQA-NLE datasets.

    Python 3

  2. SEACrowd/seacrowd-datahub SEACrowd/seacrowd-datahub Public

    A collaborative project to collect datasets in SEA languages, SEA regions, or SEA cultures.

    Python 92 57

  3. worldcuisines/worldcuisines worldcuisines/worldcuisines Public

    WorldCuisines is an extensive multilingual and multicultural benchmark that spans 30 languages, covering a wide array of global cuisines. Best Theme Paper ๐Ÿ† NAACL 2025

    Jupyter Notebook 22 3

  4. datarubrics/datarubrics datarubrics/datarubrics Public

    DataRubrics, a structured framework for assessing the quality of both human- and model-generated datasets. Leveraging recent advances in LLM-based evaluation.

    Jupyter Notebook 13 1

  5. mllm-playground mllm-playground Public

    Jupyter Notebook