BIFOLD at ICLR 2025
The BIFOLD research groups Machine Learning and Explainable Machine Learning in Medicine will participate in ICLR 2025, contributing eight papers, one blog article, and one talk. The Thirteenth International Conference on Learning Representations (ICLR 2025) is scheduled for April 24 – April 28 in Singapore.
The ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in artificial intelligence, statistics, and data science, as well as critical application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.
Below, we provide a list of contributions sorted by research group:
- Talk: Explainable AI for Unsupervised Learning:Turning Raw Data into Scientific Insights
By: Grégoire Montavon
Event: ICLR 2025 Workshop: XAI4Science
-
Title: Navigating Neural Space: Revisiting Concept Activation with Pattern-Based Probes
Authors: Frederik Pahde, Maximilian Dreyer, Moritz Weckbecker, Leander Weber, Christopher J. Anders, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
Type: Main Conference Paper
DOI: Link
Code: GitHub -
Title: Cat, Rat, Meow: On the Alignment of Language Models with Representations of Visual Brains
Authors: Lorenz Linhardt, Tom Neuhäuser, Lenka Tětková, Wieland Brendel
Presenter: Lorenz Linhardt
Type: Poster, Workshop Paper — ICLR 2025 Workshop on Representational Alignment
DOI: Link -
Title: Latent Diffusion U-Net Representations Contain Intrinsic Geometry
Authors: Jonas Loos, Lorenz Linhardt
Presenter: Jonas Loos
Type: Poster, Workshop Paper — ICLR 2025 Workshop on Deep Generative Model in Healthcare
DOI: Link -
Title: Efficient and Flexible Neural Network Training on Large Graphs via Graph Corelets
Authors: Leander Weber, Jim Berend, Moritz Weckbecker, Alexander Binder, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
Type: Workshop Paper — ICLR 2025 Workshop: XAI4Science
DOI: Link -
Title: Fractional Brownian Bridges for Aligned Data
Authors: Gabriel Nobis, Arina Belova, Maximilian Springenberg, Rembert Daems, Christoph Knochenhauer, Manfred Opper, Tolga Birdal, Wojciech Samek
Type: Workshop Paper— ICLR 2025 Workshop on Learning Meaningful Representation
DOI: Link -
Title: Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers
Authors: Johanna Vielhaben, Dilyara Bareeva, Jim Berend, Wojciech Samek, Nils Strodthoff
Type: Workshop Paper — ICLR 2025 Workshop on Representational Alignment (Re-Align)
DOI: Link -
Title: ASIDE: Architectural Separation of Instructions and Data in Language Models
Authors: Egor Zverev, Evgenii Kortukov, Alexander Panfilov, Soroush Tabesh, Sebastian Lapuschkin, Wojciech Samek, Christoph H. Lampert
Type: Workshop Paper — ICLR 2025 Workshop on Building Trust in LLMs
DOI: Link -
Title: Multilevel Generative Samplers for Investigating Critical Phenomena
Authors: Ankur Singha, Elia Cellini, Kim A. Nicoli, Karl Jansen, Stefan Kühn, Shinichi Nakajima
Presenter: Ankur Singha, Kim Nicoli
Type: Poster
DOI: Link -
Title: An Illustrated Guide to Automatic Sparse Differentiation
Authors: Adrian Hill, Guillaume Dalle, Alexis Montoison
Type: Blog Article
DOI: Link
Code: Link
-
Lukas Muttenthaler supports the event as Co-Organizer in "ICLR 2025 Workshop on Representational Alignment". More Info