TimeAuthorsTitle
15:45-16:00Khawla Elhadri, Jörg Schlötterer and Christin SeifertXNNTab — Interpretable Neural Networks for Tabular Data using Sparse Autoencoders
16:00-16:15Xinyu Sun, Xinyu Wang, Keqin Zhang, Jian Chu, Gengke Yang, Chengguang Wang and Richard JiangAnalyzing Latent Manifold Paths towards Geometric Transparency for Explainable 3D Point Cloud Generation
16:15-16:30Oussama Bouanani, Jim Berend, Wojciech Samek, Sebastian Lapuschkin and Maximilian DreyerContrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
16:30-16:45Stefan Arnold and Rene GröbnerLocating and Editing Figure-Ground Organization in Vision Transformers
16:45-17:00Vikram Sunkara, Atefe Rostami, Christoph von Tycowicz and Christof SchuetteStop throwing away your Decoder; extract the learnt local coordinate system using Latent-XAI

Event Timeslots (1)

CAELIUS
-
CHAIR: