iiinova — where your digital self keeps evolving

Jascha Achterberg @achterbrain.bsky.social · 09/03/2026

Thank you! Looking forward to seeing you there!

Reposted by Jascha Achterberg

Nicolas Skatchkovsky @nskat.bsky.social · 09/03/2026

We're organising a #Cosyne workshop on biologically-inspired AI on Monday 16th with @achterbrain.bsky.social! 🧠 We've got an incredibly exciting array of speakers, and you have the possibility to sign up to present your poster on #NeuroAI! More info below ⬇️ #compneuro #neuroscience #neuroskyence

1125

Jascha Achterberg @achterbrain.bsky.social · 09/03/2026

Super looking forward to the workshop! Alongside the talks and poster session, we are also working on an industry careers in NeuroAI meet-up for Early Career Researchers. All details and updates can be found on our website: sites.google.com/view/cosyne-...

sites.google.com

Cosyne NeuroAI

Artificial intelligence has become a transformative force in scientific research and society at large, yet current models face significant limitations. Transformer-based large language models, despite...

040

Jascha Achterberg @achterbrain.bsky.social · 09/03/2026

We are also hosting a NeuroAI poster session during the lunch break! If you are presenting a NeuroAI-related poster at Cosyne, you are welcome to put it up in our workshop room so attendees can find relevant work they might otherwise have missed. Signup: forms.gle/kzefm2FtVuRk...

forms.gle

Present your poster at the Cosyne NeuroAI workshop on 16th March 2026

On the 16th March there will be a NeuroAI-specific workshop at Cosyne ("Biologically-inspired Artificial Intelligence: Challenges and Opportunities"; information on: https://sites.google.com/view/cosy...

140

Jascha Achterberg @achterbrain.bsky.social · 09/03/2026

...continued: Shahab Bakhtiari (University of Montreal) @shahabbakht.bsky.social Filippo Moro (Institute of Neuroinformatics, University of Zurich and ETH Zurich) Charlotte Frenkel (TU Delft) Rui Ponte Costa (University of Oxford) @somnirons.bsky.social

120

Jascha Achterberg @achterbrain.bsky.social · 09/03/2026

We have an super exciting lineup of speakers joining us: Jonathan Cornford (University of Leeds) @repromancer.bsky.social Ida Momennejad (Microsoft Research) @neuroai.bsky.social Yulia Sandamirskaya (Zurich University of Applied Sciences) Wolfgang Maass (TU Graz)

120

Jascha Achterberg @achterbrain.bsky.social · 09/03/2026

Going to Cosyne? There will be a "Biologically-inspired Artificial Intelligence: Challenges and Opportunities" workshop on Monday 16th! 🧠 Exciting lineup of speakers alongside the opportunity to present your #NeuroAI poster, more info on program & poster signup below! #compneuro #neuroscience

2478

Jascha Achterberg @achterbrain.bsky.social · 18/12/2025

Giacomo's commentary was in response to this great recent paper by Iqbal et al., also in PNAS: "Biologically grounded neocortex computational primitives implemented on neuromorphic hardware improve vision transformer performance" www.pnas.org/doi/10.1073/...

pnas.org

PNAS

Proceedings of the National Academy of Sciences (PNAS), a peer reviewed journal of the National Academy of Sciences (NAS) - an authoritative source of high-impact, original research that broadly spans...

073

Jascha Achterberg @achterbrain.bsky.social · 18/12/2025

Enjoyed @giacomoi.bsky.social commentary in PNAS on how #NeuroAI and Neuromorphic Engineering should come together to allow brain circuit motifs to positively influence the design of computing systems: Biological fidelity: The engine driving the neuromorphic renaissance www.pnas.org/doi/full/10....

pnas.org

PNAS

1153

Jascha Achterberg @achterbrain.bsky.social · 01/12/2025

Let me know if you are in San Diego for #Neurips and wanted to chat about #compneuro / #neuroAI and neuroscience-inspired computing!

060

Reposted by Jascha Achterberg

Adam J. Eisen @adamjeisen.bsky.social · 26/11/2025

How do brain areas control each other? 🧠🎛️ ✨In our NeurIPS 2025 Spotlight paper, we introduce a data-driven framework to answer this question using deep learning, nonlinear control, and differential geometry.🧵⬇️

18930

Reposted by Jascha Achterberg

Rui Ponte Costa @somnirons.bsky.social · 28/11/2025

A beautiful summary of our paper! Thank you @neurosock.bsky.social

2379

Reposted by Jascha Achterberg

Cian O'Donnell @handle.invalid · 24/11/2025

One example of how multiplexing might be implemented in the brain was shown in the great work by Thomas Akam with Dmitri Kullmann, a decade ago. The papers are cited well but the general multiplexing idea never really took the field by storm as much as it deserved www.nature.com/articles/nrn...

nature.com

Oscillatory multiplexing of population codes for selective communication in the mammalian brain - Nature Reviews Neuroscience

The function of brain oscillations remains unclear, although a role in controlling the flow of signals among anatomically connected networks has been proposed. In this Opinion article, Akam and Kullma...

2295

Reposted by Jascha Achterberg

Dan Goodman @neural-reckoning.org · 21/11/2025

Postdoc fellowship opportunity for ECRs (<3 yrs post-PhD). Note that if you want to apply to work with me as your mentor, our dept has an internal deadline of Dec 4th so please email me asap. Our internal process is shorter than the full application. 🤖🧠🧪 royalcommission1851.org/fellowships/...

royalcommission1851.org

Research Fellowships

Our Mission to “increase the means of industrial education and extend the influence of science and art upon productive industry” Supplemental Charter of 1851

1102

Jascha Achterberg @achterbrain.bsky.social · 21/11/2025

We also find that while complex regions are needed to learn complex tasks, these tasks are eventually moved toward simpler regions, similar to how you may struggle the first time when learning a new skill, but slowly get better with practice.

110

Jascha Achterberg @achterbrain.bsky.social · 21/11/2025

Furthermore, we find that these pathways mirror our expected behavior of pathways in the brain! We find that difficult tasks need to be learned in more complex regions, similar to how you need to think “harder” when learning how to solve a difficult math problem.

110

Jascha Achterberg @achterbrain.bsky.social · 21/11/2025

With these three features in place, we find that our third criterion of distinct pathways is also met. While baseline models exhibit largely random expert usage patterns, our models exhibit highly structured pathways between regions that reliably emerge during learning.

110

Jascha Achterberg @achterbrain.bsky.social · 21/11/2025

Our third contribution is expert dropout. Without this feature, we find models suffer large performance deficits when experts outside of the active pathway are disabled. However, we would want models to be primarily dependent on the experts that are most being used.

110

Jascha Achterberg @achterbrain.bsky.social · 21/11/2025

When put together, these two contributions resulted in remarkable pathway consistency in our model, which we measured by correlating the routing patterns across 10 different models trained on the same tasks.

110

Jascha Achterberg @achterbrain.bsky.social · 21/11/2025

We then identify three inductive biases that yield pathways that meet each of these criteria. The first of these is a routing loss that penalizes the use of more complex experts during training, and the second scales this loss by the model’s performance on the task being solved.

110

Jascha Achterberg @achterbrain.bsky.social · 21/11/2025

We then set three criteria to determine whether pathways had formed: (1) Consistency: Models trained on the same tasks should have similar pathways (2) Self-sufficiency: Pathways should be primarily reliant on their own experts (3) Distinctness: Many distinct pathways should be present

110

Jascha Achterberg @achterbrain.bsky.social · 21/11/2025

We first needed to create a model in which we could study pathway formation. We chose a Heterogeneous Mixture-of-Experts architecture, in which information can be dynamically routed to computational experts, or regions, of varying sizes. We train model on 82 tasks of varying complexity (ModCog)!

110

Jascha Achterberg @achterbrain.bsky.social · 21/11/2025

Brains have many pathways / subnetworks but which principles underlie their formation? In our #NeurIPS paper lead by Jack Cook we identify biologically relevant inductive biases that create pathways in brain-like Mixture-of-Experts models🧵 #neuroskyence #compneuro #neuroAI arxiv.org/abs/2506.02813

13712

Reposted by Jascha Achterberg

Pengfei @pengfei-sun.bsky.social · 13/11/2025

With my great advisors and colleagues, @achterbrain.bsky.social @zhe @danakarca.bsky.social @neural-reckoning.org, we show that if heterogeneous axonal delays (imprecise) can capture the essential temporal structure of a task, spiking networks do not need precise synaptic weights to perform well.

22210

Reposted by Jascha Achterberg

Martin Schrimpf @mschrimpf.bsky.social · 29/09/2025

Come be our colleague at EPFL! Several open calls for positions 🧪🧠🤖 * Neuroscience www.epfl.ch/about/workin... (deadline Oct 1) * Life Science Engineering www.epfl.ch/about/workin... * CS general call www.epfl.ch/about/workin... * Learning Sciences www.epfl.ch/about/workin...

epfl.ch

Faculty Position in Neuroscience

The School of Life Sciences at EPFL invites applications for a Tenure Track Assistant Professor position in Neuroscience. At EPFL researchers develop and apply innovative technologies to understand br...

13210

Reposted by Jascha Achterberg

Grace Lindsay @neurograce.bsky.social · 24/08/2025

ATTN🚨: I will be looking for PhD students through NYU's Center for Data Science PhD program this year. Applicants should have an interest in either NeuroAI (specifically biological attention or AI interpretability) or ML for Remote Sensing. Visit my lab website for more info: lindsay-lab.github.io

cds.nyu.edu

PhD in Data Science: Admissions Requirements | NYU CDS

Discover the PhD in Data Science requirements at NYU. Learn about deadlines, required degrees, coursework, and application details for Fall 2025 admissions.

06544

Reposted by Jascha Achterberg

Jaan Aru @jaanaru.bsky.social · 25/08/2025

Could we understand vision as a type of problem-solving? In this new paper, we develop a computational model that iteratively refines the hypothesis about the visual input with evolutionary search. www.biorxiv.org/content/10.1... work led by @tarunkhajuria.bsky.social #visionscience #neuroAI

The difficult constellation image is solved by generating candidate solutions with a GAN and refined using a genetic search conditioned on best fitting of the solution outline to the dots on the constellation image.

0133

Reposted by Jascha Achterberg

Blake Richards @tyrellturing.bsky.social · 20/08/2025

This is really funny…

1141

Jascha Achterberg @achterbrain.bsky.social · 20/08/2025

I find your point about probabilistic definition interesting -- never seen such a definition of it, but that could neatly link to my 'usefulness' framing, as for any sort of expected value computation you would need to take 'likelihood given context' into account.

020

Jascha Achterberg @achterbrain.bsky.social · 20/08/2025

Now the usefulness in program generation might sometimes align with policy compression, but that depends a lot on the given time horizon one assumes for the definition of 'usefulness'.

120

Jascha Achterberg @achterbrain.bsky.social · 20/08/2025

It also does not 100% align with my reading of it, but I found it an interesting angle. I think I find myself, naturally, being influenced by Alan Newell's take on it (which is the one John Duncan tends to reference), which is aimed at usefulness in program generation.

120

Reposted by Jascha Achterberg

Julian Togelius @togelius.bsky.social · 18/08/2025

Can large language models play simple arcade games? Kind of. Sometimes. Slowly, and not as well as a simple search algorithm. And only if you format the input right. Of course, we made a benchmark to investigate this in more detail, because that's what we do. Paper here: arxiv.org/html/2508.08...

arxiv.org

GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games

2276

Reposted by Jascha Achterberg

Steven Scholte @neurosteven.bsky.social · 17/08/2025

#CCN2025 is over. Over 5 days there were 6 fantastic keynotes, 550 posters, 3 community events, 3 keynote & tutorials, 3 generative adversarial collaborations, 8 Satellite events, 1 community lunch meeting, 1 cross-conference hackathon, 1 competition, coffee all day, stroopwafels on day 1,

1627

Reposted by Jascha Achterberg

The Viking (Gunnar Blohm) @gunnarblohm.bsky.social · 24/07/2025

I'm curious if any senior nonhuman primate Neuro-AI researchers would be interested in joining Queen's University if we were to obtain a research chair position (full professor level)? Could you please send me a confidential message to indicate your interest? Gunnar.blohm@queensu.ca

media.tenor.com

a bald man is sitting in a chair and pointing at the camera

ALT: a bald man is sitting in a chair and pointing at the camera

42424

Reposted by Jascha Achterberg

Joao Barbosa @jbarbosa.org · 10/08/2025

Sad to miss #CCN2025. It will be the 1st conference where a PhD working w/ me will speak 😭 go see Lubna's talk (Friday) about distributed neural correlates of flexible decision making in 🐒, work done in collaboration w/ @scottbrincat.bsky.social @siegellab.bsky.social & @earlkmiller.bsky.social

15918

Reposted by Jascha Achterberg

CogCompNeuro @cogcompneuro.bsky.social · 12/08/2025

The registration desk for the first day is now open! If you are looking for information to get to the venue, you can find it here: 2025.ccneuro.org/venue-inform... Look out for the CCN banners!

071

Reposted by Jascha Achterberg

CogCompNeuro @cogcompneuro.bsky.social · 01/08/2025

Less than 2 weeks until CCN 2025 in Amsterdam! Here's everything you need to know to prepare for the 8th Cognitive Computational Neuroscience conference, August 12-15 at University of Amsterdam 🧠

1193

Reposted by Jascha Achterberg

Dan Goodman @neural-reckoning.org · 29/05/2025

I wrote an article earlier in the week arguing that we need to give junior researchers more independence earlier, and this should be our focus, not moonshot mega projects led by senior researchers. I was surprised how much agreement I'm seeing. So next question: how do we do this?

510225

Reposted by Jascha Achterberg

Dan Levenstein @dlevenstein.bsky.social · 27/05/2025

#NeuroAI finds itself facing an interesting question these days: 1) which of these now-many schemes for bio-plausible credit assignment actually operate in the brain? -and if more than one- 2) how the hell do they operate when they, inevitably, interact?

4388

Jascha Achterberg @achterbrain.bsky.social · 29/05/2025

Super excited to share & discuss this work! This was co-lead with Valentina Mione, in collaboration with Makoto Kusunoki and Mark Buckley; supervised by John Duncan. The link to the paper is here: www.biorxiv.org/content/10.1... A summary is also available on my website: www.jachterberg.com/maze

jachterberg.com

Jascha Achterberg - Maze

Abstract Complex behavior calls for hierarchical representation of current state, goal, and component moves. In the human brain, a network of “multiple-demand” (MD) regions underpins cognitive control...

021

Jascha Achterberg @achterbrain.bsky.social · 29/05/2025

*Conclusions* Our work reveals a distributed frontal network with specialized yet overlapping functions for flexible control. Different regions prioritize different variables while sharing information, with orthogonal coding to minimize interference, both across time and variable-related subspaces.

100

Jascha Achterberg @achterbrain.bsky.social · 29/05/2025

*Hierarchical choice code* Temporal cross-correlation analysis revealed hierarchical coding of problem structure across all regions, with most regions being driven by temporal similarity of time windows across choices, with vlPFC also responding for the repeated order of operations across choices.

100

Jascha Achterberg @achterbrain.bsky.social · 29/05/2025

*Move codes* Next, analysing dynamics in the "Move space", we found: Move coding develops first in vlPFC before reaching dPM; other regions showed weaker move coding. "Move space" generally orthogonal to "Goal space" (except in dmPFC).

100

Jascha Achterberg @achterbrain.bsky.social · 29/05/2025

*Goal and location codes* We projected neural activity into the "Goal space" & measured distances between projections grouped by current position vs. goal. We saw regional specialization: vlPFC driven by location; dmPFC more driven by goal (maintained throughout trial); dPM & I/O with mixed code.

100