iiinova — where your digital self keeps evolving

Reposted by Harini Sudha

Jan Lause @janlause.bsky.social · 09/06/2026

Meet Eyewire II: a new connectomic resource for the mouse retina. ~1 mm² of retina at nanometer resolution, with synapses and circuits of ca. 100,000 neurons, plus visual responses from the ~400 neurons shown in the video! Preprint: doi.org/10.64898/202... Data: eyewire.ai 🧠📈 🧠💻🧪 #VisionScience

25221

Reposted by Harini Sudha

Sebastian Damrich @sdamrich.bsky.social · 13/11/2025

🎓 We're hiring two PhD students in #MachineLearning for my new group at the Hertie Institute for AI in Brain Health, University of Tübingen! Work on unsupervised learning, #DeepLearning, and #Neuroscience in a vibrant research environment. 👇 Details below

2103

Reposted by Harini Sudha

Python Software Foundation @python.org · 27/10/2025

TLDR; The PSF has made the decision to put our community and our shared diversity, equity, and inclusion values ahead of seeking $1.5M in new revenue. Please read and share. pyfound.blogspot.com/2025/10/NSF-... 🧵

python.org

The official home of the Python Programming Language

12363752726

Reposted by Harini Sudha

Viet Anh Khoa Tran @ktran.de · 10/06/2025

New #NeuroAI preprint on #ContinualLearning! Continual learning methods struggle in mostly unsupervised environments with sparse labels (e.g. parents telling their child the object is an 'apple'). We propose that in the cortex, predictive coding of high-level top-down modulations solves this! (1/6)

1225

Reposted by Harini Sudha

Shahab Bakhtiari @shahabbakht.bsky.social · 14/05/2025

Check out our new paper! Vision models often struggle with learning both transformation-invariant and -equivariant representations at the same time. @hafezghm.bsky.social shows that self-supervised prediction with proper inductive biases achieves both simultaneously. (1/4) #MLSky #NeuroAI

24513

Reposted by Harini Sudha

Joao Barbosa @jbarbosa.org · 03/05/2025

"Our results demonstrate that the better a model understands the data, the more effectively it can compress it, suggesting a deep connection between understanding and compression." - such a cool implication

3204

Reposted by Harini Sudha

Max Forbes @maxwellforbes.com · 11/04/2025

complete blog post is now live! more tips, and reframed into 2-step process: (1) get accepted by page 1, (2) avoid rejection with the rest. download both PDFs too. maxwellforbes.com/posts/how-to...

maxwellforbes.com

The PhD Metagame: How to Get Your Paper Accepted: Page 1 Accepts, the Rest Avoids Reject - Maxwell Forbes

In 2019, I submitted a paper that was rejected with review scores 2.5, 3, 3. One week later, I resubmitted it with minor...

1184

Reposted by Harini Sudha

Billie Lauren Hindle 🏳️‍⚧️🎙️ | 🩷BWT Alpine💙 @billielhindle.bsky.social · 29/03/2025

There’s no such thing as A.I “art.” It’s a soulless amalgamation of plagiarised data. That is the antithesis of art.

3488701531

Harini Sudha @yoursharini.bsky.social · 29/03/2025

I'm interested in doing a PhD in your group. Sent you an email, looking forward to your reply :)

000

Reposted by Harini Sudha

Thomas Wolf @thomwolf.bsky.social · 19/02/2025

After 6+ months in the making and over a year of GPU compute, we're excited to release the "Ultra-Scale Playbook": hf.co/spaces/nanot... A book to learn all about 5D parallelism, ZeRO, CUDA kernels, how/why overlap compute & coms with theory, motivation, interactive plots and 4000+ experiments!

hf.co

The Ultra-Scale Playbook - a Hugging Face Space by nanotron

The ultimate guide to training LLM on large GPU Clusters

217952