Research Areas

Research areas connected to the doctoral research agenda.

My research focuses on trustworthy multimodal AI, particularly large vision-language models, with an emphasis on privacy-aware reasoning, adversarial robustness, and long-horizon visual understanding.

Privacy-Aware Vision-Language Reasoning

I study how vision-language models can remain useful while reasoning about privacy-sensitive visual information in a more controlled and reliable way.

Privacy boundariesInformation disclosurePrivacy-aware alignment

Adversarial Robustness & Security

I study both adversarial attacks and defenses for vision and vision-language models, with a focus on understanding model vulnerabilities and improving robustness.

Transferable attacksPurificationDetection

Long-Horizon Video Understanding

I study how multimodal systems can understand and reason over extended egocentric video histories while maintaining useful and privacy-aware behavior.

Egocentric VideoQAExtended contextUtility and privacy

Public Artifacts

Papers first; code and demos when public.

For now, publications are the stable public artifacts. Once code, demos, datasets, slides, or approved figures are public, this page can expand into a richer project hub.

View Publications Contact for Collaboration