Projects

• 👁️👂 From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs
  Tracing how audio and visual information is routed through audio-visual LLMs, and when those tokens stop being needed.
• 👀 The Hidden Evolution of Disguised Visual Context inside the VLM
  A study of how different vision integration paradigms behave in VLMs, and how each one transforms the visual representation inside the LLM.
• 🥤 CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks
  A PEFT framework that extends LoRA with a dedicated inter-modal adaptation pathway, for adapting dual-stream unimodal encoders to multimodal tasks.