3 papers
cs.CV2026
Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions
Xiaoxiao Sun, Mingyang Li, Kun Yuan +7
Large Vision-Language Models (VLMs) often answer classic visual illusions "correctly" on original images, yet persist with the same responses when illusion factors are inverted, ev…
cs.CV2025
Universal Visuo-Tactile Video Understanding for Embodied Interaction
Yifan Xie, Mingyang Li, Shoujie Li +5
Tactile perception is essential for embodied agents to understand physical attributes of objects that cannot be determined through visual inspection alone. While existing approache…
cs.CV2025
Unpaired Translation of Point Clouds for Modeling Detector Response
Mingyang Li, Michelle Kuchera, Raghuram Ramanujan +3
Modeling detector response is a key challenge in time projection chambers. We cast this problem as an unpaired point cloud translation task, between data collected from simulations…