← Search

Adam Pardyl

2 accepted papers

2025

FlySearch: Exploring how vision-language models explore

NeurIPS 2025poster

The real world is messy and unstructured. Uncovering critical information often requires active, goal-driven exploration. It remains to be seen whether Vision-Language Models (VLMs), which recently emerged as a popular zero-shot tool in many difficult tasks, can operate effectively in such condition…

Cited by 0SourcecodeScholar
2023

Active Visual Exploration Based on Attention-Map Entropy

IJCAI 2023poster

Active visual exploration addresses the issue of limited sensor capabilities in real-world scenarios, where successive observations are actively chosen based on the environment. To tackle this problem, we introduce a new technique called Attention-Map Entropy (AME). It leverages the internal uncerta…