activity
20242026
collaborators

13 papers

cs.CV2026

LinguDistill: Recovering Linguistic Ability in Vision-Language Models via Selective Cross-Modal Distillation

Patrick Amadeus Irawan, Erland Hilman Fuadi, Shanu Kumar +2

Adapting pretrained language models (LMs) into vision-language models (VLMs) can degrade their native linguistic capability due to representation shift and cross-modal interference…

cs.AI2026

Anthropogenic Regional Adaptation in Multimodal Vision-Language Model

Samuel Cahyawijaya, Peerat Limkonchotiwat, Tack Hwa Wong +45

While the field of vision-language (VL) has achieved remarkable success in integrating visual and textual information across multiple languages and domains, there is still no dedic…

cs.CV2026

Counting to Four is still a Chore for VLMs

Duy Le Dinh Anh, Patrick Amadeus Irawan, Tuan Van Vo

Vision--language models (VLMs) have achieved impressive performance on complex multimodal reasoning tasks, yet they still fail on simple grounding skills such as object counting. E…

cs.CL2026

M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG

David Anugraha, Patrick Amadeus Irawan, Anshul Singh +2

Vision-language models (VLMs) have achieved strong performance in visual question answering (VQA), yet they remain constrained by static training data. Retrieval-Augmented Generati…

cs.CL2026

Can Large Language Models Understand, Reason About, and Generate Code-Switched Text?

Genta Indra Winata, David Anugraha, Patrick Amadeus Irawan +15

Code-switching is a pervasive phenomenon in multilingual communication, yet the robustness of large language models (LLMs) in mixed-language settings remains insufficiently underst…

cs.CV2025

Vision Language Models are Confused Tourists

Patrick Amadeus Irawan, Ikhlasul Akmal Hanif, Muhammad Dehan Al Kautsar +3

Although the cultural dimension has been one of the key aspects in evaluating Vision-Language Models (VLMs), their ability to remain stable across diverse cultural inputs remains l…