Call For Papers

Discover why, when and how distinct learning processes yield similar representations, and the degree to which these can be unified.

Neural models, whether biological or artificial, tend to develop structurally similar representations when exposed to semantically similar stimuli. This convergence is a common yet enigmatic phenomenon, sparking increasing interest in Neuroscience, Artificial Intelligence, and Cognitive Science. This workshop aims to get a unified view on this topic and facilitate the exchange of ideas and insights across these fields, focusing on three key points:

When: Understanding the patterns by which these similarities emerge in different neural models and developing methods to measure them.

Why: Investigating the underlying causes of these similarities in neural representations, considering both artificial and biological models.

What for: Exploring and showcasing applications in modular deep learning, including model merging, reuse, stitching, efficient strategies for fine-tuning, and knowledge transfer between models and across modalities.

🔭 Topics of Interest 🔬

A non exhaustive list of the preferred topics include:

Model merging, stitching and compositionality Techniques and strategies for combining, aligning, or transferring knowledge between neural models.
Representational alignment Methods, theories, and measures for relating and aligning representations across different neural networks.
Identifiability in neural models Studying when learned representations are uniquely determined, and therefore comparable across models, up to specific transformations.
Symmetry and equivariance in NNs Studying transformations and invariances that explain when representations across different models can be related or unified.
Learning dynamics Understanding the training processes and dynamics that lead different neural models to develop similar representations.
Multimodal learning Techniques that align or fuse information across modalities towards shared or comparable multimodal representations.
Multi-agent communication Studying how communication enables agents to align meanings and predictive representations across their latent spaces.
Disentangled representations Studying structured representations whose shared factors can facilitate comparison and alignment across different neural models.
Multiview representation learning Approaches for learning shared representations from data acquired under different conditions or modalities.
Representation Similarity Analysis Assessing how representations across different neural systems relate by comparing their responses to similar stimuli.
Linear Mode Connectivity Exploring how solutions in weight space are connected and how such connectivity relates representations across trained models.
Mechanistic Interpretability Studying whether circuits, features, and computations can be related across models through shared or aligned representations.
Similarity measures in NNs Metrics for quantifying when neural models can be related at the weight, functional, or representation level.
Representation universality Investigating whether different models converge toward shared representations as scale, data, and modalities vary.

🔴 Full Paper (Archival)

This track will address complete papers to be published in a dedicated workshop proceedings volume (last year’s proceedings can be found here).

Full papers should be at most 9 pages in main text length (i.e., excluding references and appendix) and anonymized.

🔵 Extended Abstract (Non-Archival)

This track aims to address early-stage results, insightful negative findings, and opinion pieces.

Extended abstracts should be at most 4 pages in main text length (i.e., excluding references and appendix) and anonymized.

Both tracks will be featured in the workshop poster session to give the authors the opportunity to present their work, and a subset of the submissions will be selected for a spotlight talk session during the workshop.

For both tracks, please make sure to use the NeurIPS LaTeX template. For camera ready submissions please refer to the section below (TBD). The NeurIPS checklist doesn’t need to be included in submissions to the workshop.

⚠️ Important Dates 📅

  • Technical paper submission deadline: Oct 4 AoE Submit on OpenReview
  • Final decisions to authors: TBD AoE

👥 Join the Program Committee

We believe that maintaining high review quality is crucial, and one of the best ways to achieve this is by keeping the review load manageable for each reviewer: in the last years, we ensured that no reviewer was assigned more than two papers, with at most one full paper, thanks to our great Program committees of 2023, 2024 and 2025. To continue this approach, we are seeking new members of the Program Committee who share a passion for these topics and are eager to contribute.

Additionally, believing reviewers to deserve recognition for their hard work, we’re working to introduce prizes for outstanding reviewers. Stay tuned for more details!

If you’re interested in joining our Program Committee, sign up here!