Tim Kietzmann

Hi, we will have three NeuroAI postdoc openings (3 years each, fully funded) to work with Sebastian Musslick (@musslick.bsky.social), Pascal Nieters and myself on task-switching, replay, and visual information routing.

Reach out if you are interested in any of the above, I'll be at CCN next week!

Do come and talk to us about any of the above and whatever #NeuroAI is on your mind. Excited for this upcoming #CCN2025, and looking forward to exchanging ideas with all of you.

All posters can be found here: www.kietzmannlab.org/ccn2025/

And last but not least Fraser Smith's work on understanding how occluded objects are represented in visual cortex.

Time: Tuesday, August 12, 1:30 – 4:30 pm
Location: A66, de Brug & E‑Hall

Please also check out Songyun Bai's poster on further AVS findings that we were involved in: Neural oscillations encode context-based informativeness during naturalistic free viewing.

Time: Tuesday, August 12, 1:30 – 4:30 pm
Location: A165, de Brug & E‑Hall

Friday keeps on giving. Interested in representational drift in macaques? Then come check out Dan's (@anthesdaniel.bsky.social) work providing first evidence for a sequence of three different, yet comparatively stable clusters in V4.

Time: August 15, 2-5pm
Location: Poster C142, de Brug & E‑Hall

Another Friday feat: Philip Sulewski's (@psulewski.bsky.social) and @thonor.bsky.social's
modelling work. Predictive remapping and allocentric coding as consequences of energy efficiency in RNN models of active vision

Time: Friday, August 15, 2:00 – 5:00 pm,
Location: Poster C112, de Brug & E‑Hall

Also on Friday, Victoria Bosch (@initself.bsky.social) presents her superb work on fusing brain scans with LLMs.

CorText-AMA: brain-language fusion as a new tool for probing visually evoked brain responses

Time: 2 – 5 pm
Location: Poster C119, de Brug & E‑Hall
2025.ccneuro.org/poster/?id=n...

On Friday, Carmen @carmenamme.bsky.social has a talk & poster on exciting AVS analyses. Encoding of Fixation-Specific Visual Information: No Evidence of Information Carry-Over between Fixations

Talk: 12:00 – 1:00 pm, Room C1.04
Poster: C153, 2:00 – 5:00 pm, de Brug &E‑Hall
www.kietzmannlab.org/avs/

Also on Tuesday, Rowan Sommers will present our new WiNN architecture. Title: Sparks of cognitive flexibility: self-guided context inference for flexible stimulus-response mapping by attentional routing

Time: August 12, 1:30 – 4:30 pm
Location: A136, de Brug & E‑Hall

On Tuesday, Sushrut's (@sushrutthorat.bsky.social) Glimpse Prediction Networks will make their debut: a self-supervised deep learning approach for scene-representations that align extremely well with human ventral stream.

Time: August 12, 1:30 – 4:30 pm
Location: A55, de Brug & E‑Hall

In the "Modeling the Physical Brain" event, I will be speaking about our work on topographic neural networks.

Time: Monday, August 11, 11:30 am – 6:00 pm
Location: Room A2.07
Paper: www.nature.com/articles/s41...

First, @zejinlu.bsky.social will talk about how adopting a human developmental visual diet yields robust, shape-based AI vision. Biological inspiration for the win!

Talk Time/Location: Monday, 3-6 pm, Room A2.11
Poster Time/Location: Friday, 2-5 pm, C116 at de Brug & E‑Hall

OK, time for a CCN runup thread. Let me tell you about all the lab’s projects present at CCN this year. #CCN2025

Using AI to 'see' what we see Fed the right information, large language models can match what the brain sees when it takes in an everyday scene such as children playing or a big city skyline, a new study led by Ian Charest finds.

#AI "Ultimately, this is a step forward in understanding how the human brain understands meaning from the visual world." #LLMs @mila-quebec.bsky.social @adriendoerig.bsky.social @timkietzmann.bsky.social @natmachintell.nature.com
nouvelles.umontreal.ca/en/article/2...

A long time coming, now out in @natmachintell.nature.com: Visual representations in the human brain are aligned with large language models.

Check it out (and come chat with us about it at CCN).

For completeness sake: we know the other team and cite both of their papers in the preprint.

Devil is in the details as usual.

They (and others) focused on acuity, while we show that the actual gains do not come from acuity but the development of contrast sensitivity.

To be honest, so far it has exceeded our expectations across the board.

A big surprise was that visual acuity (i.e. initial blurring) had so little impact. This is what others had focused on in the past. Instead, the development of contrast sensitivity gets you most of the way there.

Exciting new preprint from the lab: “Adopting a human developmental visual diet yields robust, shape-based AI vision”. A most wonderful case where brain inspiration massively improved AI solutions.

Work with @zejinlu.bsky.social @sushrutthorat.bsky.social and Radek Cichy

arxiv.org/abs/2507.03168

Thank you!

We are incredibly excited about this because DVD may offer a resource-efficient path towards safer, more human-like AI vision — and suggests that biology, neuroscience, and psychology have much to offer in guiding the next generation of artificial intelligence. #NeuroAI #AI /fin

In summary, DVD-training yields models that rely on a fundamentally different feature set, shifting from distributed local textures to integrative, shape-based features as the foundation for their decisions. 9/

Result 4: How about adversarial robustness? DVD-trained models also showed greater resilience to all black- and white-box attacks tested, performing 3–5 times better than baselines under high-strength perturbations. 8/

Result 3: DVD-trained models exhibit more human-like robustness to Gaussian blur compared to baselines, plus an overall improved robustness to all image perturbations tested. 7/

Result 2: DVD-training enabled abstract shape recognition in cases where AI frontier models, despite being explicitly prompted, fail spectacularly.

t-SNE nicely visualises the fundamentally different approach of DVD-trained models. 6/

Layerwise relevance propagation revealed that DVD-training resulted in a different recognition strategy than baseline controls: DVD-training puts emphasis on large parts of the objects, rather than highly localised or highly distributed features. 5/

Result 1: DVD training massively improves shape-reliance in ANNs.

We report a new state of the art, reaching human-level shape-bias (even though the model uses orders of magnitude less data and parameters). This was true for all datasets and architectures tested 4/

We then test the resulting DNNs across a range of conditions, each selected because they are challenging to AI: (i) shape-texture bias, (ii) recognising abstract shapes embedded in complex backgrounds, (iii) robustness to image perturbations, and (iv) adversarial robustness, 3/

The idea: instead of high-fidelity training from the get-go (the gold standard), we simulate the visual development from newborns to 25 years of age by synthesising decades of developmental vision research into an AI preprocessing pipeline (Developmental Visual Diet - DVD) 2/

Exciting new preprint from the lab: “Adopting a human developmental visual diet yields robust, shape-based AI vision”. A most wonderful case where brain inspiration massively improved AI solutions.

Work with @zejinlu.bsky.social @sushrutthorat.bsky.social and Radek Cichy

arxiv.org/abs/2507.03168