Machine and Hybrid
Intelligence Lab
Lab workspace

Two papers at ECCV 2026

Lab members contributed work on vision-language model reliability and human-inspired visual search, including a paper at the Human Inspired Computer Vision Workshop.

Diagram of local data, local model training, and shared parameter updates.
Conceptual research schematic.

  • ESC: Emotional Self-Correction for Reliable Vision-Language Models

    Authors: Tien-Huy Nguyen, Minh-Nhat Nguyen, Nguyen Nhat Huy, Hung Viet Nguyen, Huy Nguyen Minh Nhat, Thanh-Huy Nguyen, Cuong Tuan Nguyen, Hoang M. Le, Dat Nguyen, Phat Kim Huynh, Min Xu, Ulas Bagci

  • Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans

    Authors: Mohamed Amine KERKOURI, Marouane Tliba, Aladine Chetouani, Ulas Bagci, Alessandro Bruno
    (HUMAN-INSPIRED COMPUTER VISION)