Research

2026

• CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks
  Suharitdamrong, W., Alex, T., Awais, M., Atito, S.
  ICML, 2026
  arXivcodeproject

Preprints

• Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization
  Alex, T., Suharitdamrong, W., Atito, S., Mustafa, A., Awais, M., Jackson, P. J. B., Deng, J., Elezi, I.
  arXiv preprint (under review)
  arXivcode
• The Hidden Evolution of Disguised Visual Context inside the VLM
  Suharitdamrong, W., Alex, T., Zhu, X., Awais, M., Atito, S.
  arXiv preprint (under review)
  arXivproject
• From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs
  Suharitdamrong, W., Awais, M., Zhu, X., Atito, S.
  arXiv preprint (under review)
  arXiv
• PAL: Probing Audio Encoders via LLMs - Audio Information Transfer into LLMs
  Alex, T.^*, Suharitdamrong, W.^*, Atito, S., Mustafa, A., Jackson, P. J. B., Razzak, I., Awais, M.
  arXiv preprint (under review)
  ^*Equal contribution
  arXivcode