Poster · Sydney

Few Contrastive Attention Heads Enable Visual Grounding in Large Vision-Language Models

Name: Few Contrastive Attention Heads Enable Visual Grounding in Large Vision-Language Models
Start: 2026-12-10T17:00:00+11:00
End: 2026-12-10T20:00:00+11:00
Location: Hall 1-4, ICC Sydney

When: Thu 10 Dec 2026, 17:00–20:00 AEDT
Where: Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session: Sydney Poster Session 6
Authors: Neha Sengar, Andres Saurez, Dongsoo Har, Sangkeum Lee
Organisations: KAIST
QRS classification: Attention and transformers, Language models, Computer vision

Open in schedule Official page