🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Very insightful work

Exciting opportunity for viral engineering wizards to come join our mission to map the mouse brain!

Transformers employ different strategies through training to minimize loss, but how do these tradeoff and why? Excited to share our newest work, where we show remarkably rich competitive and cooperative interactions (termed "coopetition") as a transformer learns. Read on 🔎⏬

A must read from AntonioFR and team!

Check out replay making new place cells (likely from compositional elements!).

Want to procedurally generate large-scale relational reasoning experiments in natural language, to study human psychology 🧠 or eval LLMs 🤖? We have a tool for that! github.com/google-deepmin… Check out Kenneth Marino's thread for some stuff you can do:

At #Cosyne2025? Come by my poster today (47) to hear how sequential predictive learning produces a continuous neural manifold that can generate replay during sleep, and spatial representations that "sweep" ahead to future positions. All from sensory information + action!

.Chongxi Lai works at the intersection of neuroscience, AI, and brain-machine interfaces. He researches building brain-like models in a simulated environment, to test whether cognition can be enhanced through novel AI-assisted BMI closed-loop stimulation algorithms.

Thrilled to announce I've joined Astera Institute's first residency cohort! Excited to collaborate with this amazing team to build technology for a brighter future! I will focus on building and testing brain-like model in large-scale simulation and use AI to enhance it!

Exciting opportunity, come join us!

Our latest study identifies a specific cell type and receptor essential for psilocybin’s long-lasting neural and behavioral effects 🍄🔬🧠🐁 Led by Ling-Xiao Shao and Clara Liao Funded by NIH National Institute of Mental Health (NIMH) 📄Read in nature - nature.com/articles/s4158… 1/12

New preprint! Intelligent creatures can solve truly novel problems (not just variations of previous problems), zero-shot! Why? They can "think" before acting, i.e. mentally simulate possible behaviors and evaluate likely outcomes How can we build agents with this ability?

Seize the chance to work with the best!

From our team at Google DeepMind: we ask, as an LLM continues to learn, how do new facts pollute existing knowledge? (and can we control it) We investigate such hallucinations in our new paper, to be presented as Spotlight at ICLR 2026 next week.

(Plz repost) I’ve been receiving some good news lately and will be hiring at all levels to expand the lab. Please get in contact if you are interested in reinforcement learning, neural plasticity, circuit dynamics, and/or hearing rehabilitation. pierre.apostolides @ umich .edu

This preprint is now published at nature. With current and former DeepMinders Yuval Tassa, Josh Merel, Matt Botvinick, and my HHMI | Janelia colleagues Roman Vaxenburg, Igor Siwanowicz, Kristin Branson @[email protected], Michael Reiser | michaelreiser.bsky.social, Gwyneth Card and more

Cool work from HHMI | Janelia .. "cognitive graphs of latent structure" .... Looks like even more evidence for CSCG-like representation and schemas. (science.org/doi/10.1126/sc…, arxiv.org/abs/2302.07350) biorxiv.org/content/10.110…

How does in-context learning emerge in attention models during gradient descent training? Sharing our new Spotlight paper ICML Conference: Training Dynamics of In-Context Learning in Linear Attention arxiv.org/abs/2501.16265 Led by Yedi Zhang with Aaditya Singh and Peter Latham

New paper: World models + Program synthesis by Wasu Top Piriyakulkij 1. World modeling on-the-fly by synthesizing programs w/ 4000+ lines of code 2. Learns new environments from minutes of experience 3. Positive score on Montezuma's Revenge 4. Compositional generalization to new environments