We’re excited to announce the first workshop on CogInterp: Interpreting Cognition in Deep Learning Models @ NeurIPS 2025! 📣. How can we interpret the algorithms and representations underlying complex behavior in deep learning models?. 🌐 1/.

Due to popular demand, we are extending the CogInterp submission deadline again! Submit by 8/27 (midnight AoE).

📆 The deadline for submission to CogInterp has officially been extended to 8/22 (midnight AoE). We look forward to seeing what you all submit!.

Join us at NeurIPS in San Diego this December for talks by top experts in the field, including James McClelland, Chris Potts (@ChrisGPotts), Stephanie Chan (@scychan_brains), and Ari Holtzman (@universeinanegg). 📅  Submit your 4-page paper (non-archival) by August 15!.

We’re bringing together researchers in fields such as machine learning, psychology, linguistics, and neuroscience to discuss new empirical findings which help us interpret high-level abilities in deep learning models. 3/.

Deep learning models such as LLMs demonstrate impressive capabilities and a timely challenge is to understand the intermediate processes enabling them. Cognitive science offers a rich body of theories, experiments and frameworks which may be adopted to answer these questions. 2/.