2026
What "Not" to Detect: Negation-Aware VLMs via Structured Reasoning and Token Merging
ICLR 2026poster
State-of-the-art vision-language models (VLMs) suffer from a critical failure in understanding negation, often referred to as affirmative bias. This limitation is particularly severe in described object detection (DOD) tasks. To address this, we propose two primary contributions: (1) a new dataset p…