Harrison Ritz

Medial PFC interacts with the hippocampus to retrieve context-congruent memories.. but HOW?? was what started this. Simulating mPFC-HIP🧠, we designed an RNN🤖 that retrieves memories similar in context, on top of self-attention. It learns to retrieve like humans faster! arxiv.o…

A neural network that maintains and retrieves memories based on context arxiv.org

I've only read the introduction so far but it's already worth sharing, just beautiful arxiv.org/abs/2611.14381

Optimization principles, revisited arxiv.org

𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗱𝘆𝗻𝗮𝗺𝗶𝗰𝗮𝗹 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 𝗶𝘀 𝗵𝗮𝗿𝗱 But lots of progress being made; this one looks very interesting. arxiv.org/abs/2604.24662

Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data arxiv.org

How do time series foundation models forecast unseen dynamical systems? In new experiments, we find that small transformers learn to approximate transfer operators in-context. (1/N) arxiv.org/abs/2602.18679

Transformers for dynamical systems learn transfer operators in-context arxiv.org

BayesFlow 2.1.0 is now live! 🚀 Our new major release includes lots of goodies: differentiable adapters, better inference network featuring Mean Flow, unified masking, redesigned multilevel inference, and much more! 🎉 The sky is the limit. And as always, keep rocking! 😎 github.…

GitHub - bayesflow-org/bayesflow: A Python library for simulation-based inference with deep learning github.com

New preprint from Kieran: We introduce a new data-driven method, feature-based slow feature analysis (f-SFA), to track non-stationarity from time-series data (with no generative model). It beats benchmarks on chaotic systems and tracks sleep depth continuously from EEG. arxiv.…

Parameter inference from a non-stationary unknown process using statistical feature-based slow feature analysis arxiv.org

📣 Save the date! RLDM 2027, the Multi-disciplinary Conference on Reinforcement Learning and Decision Making, is coming to Paris, July 6-9, 2027 🎉 Stay tuned for submission deadlines and more updates on our website rldm.org 👀

RLDM | The Multi-disciplinary Conference on Reinforcement Learning and Decision Making rldm.org

this is actually a very good article

How LLMs Actually Work 0xkato.xyz

Twelve quick tips for AI-assisted coding in science journals.plos.org/ploscompbiol... - our latest by @ericwbridgeford.bsky.social with @thisisadax.bsky.social , Zijiao Chen, Zhicheng Lin, @hritz.bsky.social and @joachim.cidlab.com

Twelve quick tips for AI-assisted coding in science journals.plos.org

How fast we decide reveals how we learn. New in @plos.org #PLoSCompBio : modeling response times alongside choices disentangles working memory, reinforcement learning and cognitive control, and reveals differences in schizophrenia that choices alone missed. 🧵 t.co/BTOgmpd4YH

Modeling decision dynamics disentangles working memory, cognitive control and reinforcement learning and reveals clinical differences t.co

How fast we decide reveals how we learn. New in @plos.org #PLoSCompBio : modeling response times alongside choices disentangles working memory, reinforcement learning and cognitive control, and reveals differences in schizophrenia that choices alone missed. 🧵 t.co/BTOgmpd4YH

Modeling decision dynamics disentangles working memory, cognitive control and reinforcement learning and reveals clinical differences journals.plos.org

Check out my critique of prediction studies in NeuroAI (along with Guillermo Puebla, Sushrut Thorat, Konstantinos Tsetsos, and Casimir Ludwig) osf.io/preprints/ps...

OSF osf.io