 Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency PartitionComputer Vision and Pattern Recognition (CVPR), 2025 |
 LayerEdit: Disentangled Multi-Object Editing via Conflict-Aware Multi-Layer LearningConference on Empirical Methods in Natural Language Processing (EMNLP), 2025 |
![[De|Re]constructing VLMs' Reasoning in Counting](https://cdn.parameterlab.de/resized-images/aHR0cHM6Ly9jZG4ucGFyYW1ldGVybGFiLmRlL3BhcGVycy8yNTEwLjE5NTU1L3BhZ2VzL3BhZ2UuanBn?w=256&q=75&f=webp)
