Banner Banner
Icon

April 21, 2026

ICLR 2026 Conference Contributions

BIFOLD researchers will participate in ICLR 2026, contributing seven workshop papers and seven posters. The Fourteenth International Conference on Learning Representations (ICLR 2026) is scheduled for April 23 – April 27 in Rio de Janeiro, Brazil. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics, and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics. This year, 5,355 papers were accepted out of 19,525 valid submissions.

On April 14, 2026, BIFOLD organized an ICLR Pre-Fest to give several groups the opportunity to present their posters before the conference. A brief review of this event is available on our LinkedIn Channel.

Below, we provide a list of contributions sorted by type:

  1. Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamics. Winfried Ripken, Michael Plainer, Gregor Lied, J. Thorben Frank, Oliver T. Unke, Stefan Chmiela, Frank Noé, Klaus-Robert Müller
    1. https://openreview.net/forum?id=GyYTRfQEsP
    2. Website: https://ml4molsim.github.io/hamiltonian-flow-maps/ 
    3. Code: https://github.com/ML4MolSim/hamiltonian-flow-maps 
    4. Presentation Venue: Workshop AI4Mat 
    5. Presentation Date: April 26th 
    6. Type: Spotlight
  2. Revealing Task-Dependent Layer Relevance via Attentive Multi-Layer Fusion. Marco Morik, Laure Ciernik, Lukas Thede, Luca Eyring, Shinichi Nakajima, Zeynep Akata, Lukas Muttenthaler 
    1. https://openreview.net/forum?id=cc417AET6g 
    2. Presentation Date:  April 26, 2026
    3. Presentation Venue: Workshop Sci4DL
    4. Type: Poster
  3. Context Sensitivity Improves Human-Machine Visual Alignment. Frieda Born, Tom Neuhäuser, Lukas Muttenthaler, Brett D Roads, Bernhard Spitzer, Andrew Kyle Lampinen, Matt Jones, Klaus Robert Müller, Michael Curtis Mozer
    1. Link: https://openreview.net/forum?id=W3Fq26BXQ7 
    2. Presentation Date: April 27, 2026
    3. Presentation Venue: ICLR 2026 Re-Align Workshop
    4. Type: Short paper
  4. Monitoring Emergent Reward Hacking During Generation via Internal Activations. Patrick Wilhelm, Thorsten Wittkopp, Odej Kao.
    1. Link: https://arxiv.org/abs/2603.04069 
    2. Presentation Date: Apr 27, 2026
    3. Presentation Venue: Workshop Trustworthy AI
  5. Visual Disentangled Diffusion Autoencoders: Scalable Counterfactual Generation for Foundation Models. Sidney Bender, Marco Morik.
    1. Link: https://openreview.net/forum?id=tKA7DqmEI1 
    2. Presentation Date: Apr 27, 2026
    3. Presentation Venue: Workshop Trustworthy AI
  6. Protein Counterfactuals via Diffusion-Guided Latent Optimization. Weronika Kłos, Sidney Bender, Lukas Kades
    1. https://openreview.net/forum?id=s0bgDiHihZ
    2. Presentation Date: Apr 27, 2026
    3. Presentation Venue: Workshop Gen^2
  7. MapPFN: Learning Causal Perturbation Maps in Context. Marvin Sextro, Weronika Kłos, Gabriel Dernbach
    1. Link: https://arxiv.org/abs/2601.21092 
    2. Code: https://github.com/marvinsxtr/MapPFN 
    3. Presentation Date: April 27, 2026
    4. Presentation Venue: Workshop Gen^2

 

  1. Bayesian Parameter Shift Rules in Variational Quantum Eigensolvers. Samuele Pedrielli, Christopher Anders, Lena Funcke, Karl Jansen, Kim A. Nicoli, Shinichi Nakajima.
    1. Link: https://openreview.net/forum?id=NjOAQ2nJuL 
    2. Poster ID: 10008504
    3. Video: https://recorder-v3.slideslive.com/?share=108852&s=50299cc7-0e80-438b-8b8f-06a0e61bb36e
    4. Presentation Date: Thu Apr 23, 2026; Poster Session 2 (Pavilion 3 P3-#1214)
  2. ASIDE: Architectural Separation of Instructions and Data in Language Models. Egor Zverev, Evgenii Kortukov, Alexander Panfilov, Alexandra Volkova, Rush Tabesh, Sebastian Lapuschkin, Wojciech Samek, Christoph H. Lampert
    1. Link: https://arxiv.org/abs/2503.10566 
    2. Code: https://github.com/egozverev/aside 
    3. Models: https://huggingface.co/ISTA-MLCV/collections 
    4. LinkedIn: https://www.linkedin.com/feed/update/urn:li:activity:7451923430565928960/ 
    5. Presentation Date: 23 Apr,  2026; Poster P4-3910
    6. Presentation Venue: Poster Session, Pavilion 4
  3. Attribution-Guided Decoding. Piotr Komorowski, Elena Golimblevskaia, Reduan Achtibat, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek
    1. Link: https://openreview.net/forum?id=ifBXz7ABV0 
    2. Presentation Date: 23 Apr, 2026; Poster P4-4009
    3. Presentation Venue: Poster Session, Pavilion 4
  4. Circuit Insights: Towards Interpretability Beyond Activations. Elena Golimblevskaia, Aakriti Jain, Bruno Puri, Ammar Ibrahim, Wojciech Samek, Sebastian Lapuschkin
    1. https://openreview.net/forum?id=2Jyb1yu3nN 
    2. Presentation Date: 23 Apr, 2026; Poster P4-4017
    3. Presentation Venue: Poster Session, Pavilion 4
  5. Precise and Interpretable Editing of Code Knowledge in Large Language Models. Min Xue, Nikolai Bolik, Lennart Stöpler, Erik Imgrund, Janik Schmid, Artur Andrzejak
    1. Link: https://openreview.net/forum?id=diVf17SNek 
    2. Presentation Date: 23 Apr, 2026; Poster P3-709
    3. Presentation Venue: Poster Session, Pavilion 3
  6. Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP. Lorenz Hufe, Constantin Venhoff, Erblina Purelku, Maximilian Dreyer, Sebastian Lapuschkin, Wojciech Samek
    1. https://openreview.net/forum?id=UI7mbsIZeN 
    2. Presentation Date: April 25, 2026; P4-4007
    3. Presentation Venue: Poster Session, Pavilion 4
  7. Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs. Alexander Panfilov, Evgenii Kortukov, Kristina Nikolić, Matthias Bethge, Sebastian Lapuschkin, Wojciech Samek, Ameya Prabhu, Maksym Andriushchenko, Jonas Geiping
    1. https://openreview.net/forum?id=IbDr8xgUMW 
    2. Presentation Date: April 25, 2026; P4-4011
    3. Presentation Venue: Poster Session, Pavilion 4