I probably don’t agree with Charlie Kirk on a damn thing, but that doesn’t matter - he’s a husband and a father.
This is despicable and can’t become our new normal.
I probably don’t agree with Charlie Kirk on a damn thing, but that doesn’t matter - he’s a husband and a father.
This is despicable and can’t become our new normal.
It outperforms CLIP-like models (SigLip2, finetuned StreetCLIP)… and that’s shocking 🤯
Why? CLIP models have an innate advantage — they literally learn place names + images. DinoV3 doesn’t.
It outperforms CLIP-like models (SigLip2, finetuned StreetCLIP)… and that’s shocking 🤯
Why? CLIP models have an innate advantage — they literally learn place names + images. DinoV3 doesn’t.
a 9B Mamba (RNN) / Transformer hybrid architecture reasoning model from NVIDIA that beats an equivalent Qwen
6x the throughput though, bc it’s Mamba
research.nvidia.com/labs/adlr/NV...
a 9B Mamba (RNN) / Transformer hybrid architecture reasoning model from NVIDIA that beats an equivalent Qwen
6x the throughput though, bc it’s Mamba
research.nvidia.com/labs/adlr/NV...
Check out our latest paper with Adrien Cortés at @icmlconf !
Paper: arxiv.org/abs/2506.05515
Code: github.com/Victorletzel...
Poster #2211 , Tue 15 Jul 11 a.m. PDT East
#timeseries #quantization #uncertainty #icml2025
Check out our latest paper with Adrien Cortés at @icmlconf !
Paper: arxiv.org/abs/2506.05515
Code: github.com/Victorletzel...
Poster #2211 , Tue 15 Jul 11 a.m. PDT East
#timeseries #quantization #uncertainty #icml2025
jamanetwork.com/journals/jam...
We (with @tspisak.bsky.social, @christianbuchel.bsky.social) published a commentary on Chowdhury, Bi et al. (2025, JAMA Neurology) raising serious concerns about their reported results.
👇 1/13
jamanetwork.com/journals/jam...
We (with @tspisak.bsky.social, @christianbuchel.bsky.social) published a commentary on Chowdhury, Bi et al. (2025, JAMA Neurology) raising serious concerns about their reported results.
👇 1/13
Read on to learn about the exciting interplay of stochastic PDEs, Markov structures and sparse linear algebra that make it possible... 🧵 1/8
Read on to learn about the exciting interplay of stochastic PDEs, Markov structures and sparse linear algebra that make it possible... 🧵 1/8
Published in @dpn-journal.bsky.social @acnporg.bsky.social
www.nature.com/articles/s44...
Published in @dpn-journal.bsky.social @acnporg.bsky.social
www.nature.com/articles/s44...
“An Action Networks Model for Pain”
We propose a new model for chronic pain — and highlight two functionally connected cortical networks that could revolutionize how we treat it.
👉 thread below 🧵
osf.io/preprints/ps...
“An Action Networks Model for Pain”
We propose a new model for chronic pain — and highlight two functionally connected cortical networks that could revolutionize how we treat it.
👉 thread below 🧵
osf.io/preprints/ps...
Now, in new work, we show that AMN contains distinct subnetworks for making decisions, implementing actions, and processing feedback. doi.org/10.1073/pnas...
Now, in new work, we show that AMN contains distinct subnetworks for making decisions, implementing actions, and processing feedback. doi.org/10.1073/pnas...
#neurosci #consci #philsci #neuroskyence
#neurosci #consci #philsci #neuroskyence
Why are long-range connectomic interactions in the cortex dominant in shaping dynamics in some experiments but apparently negligible in others?
We (w/ R Maran, @elimuller.bsky.social) address this question by studying a new hybrid model of cortical dynamics.
arxiv.org/abs/2506.19800
Why are long-range connectomic interactions in the cortex dominant in shaping dynamics in some experiments but apparently negligible in others?
We (w/ R Maran, @elimuller.bsky.social) address this question by studying a new hybrid model of cortical dynamics.
arxiv.org/abs/2506.19800
[2-036] Contrastive-Equivariant Self-Supervised Learning Improves Alignment with Primate Visual Area IT
[2-036] Contrastive-Equivariant Self-Supervised Learning Improves Alignment with Primate Visual Area IT
When a chickadee looks at a distant location, the same place cells activate as if it were actually there 👁️
The hippocampus encodes where the bird is looking, AND what it expects to see next -- enabling spatial reasoning from afar
bit.ly/3HvWSum
When a chickadee looks at a distant location, the same place cells activate as if it were actually there 👁️
The hippocampus encodes where the bird is looking, AND what it expects to see next -- enabling spatial reasoning from afar
bit.ly/3HvWSum
@andpru.bsky.social and I provide a motor systems perspective on a proposed speed limit for human information processing. Out today in
@natneuro.nature.com:
www.nature.com/articles/s41...
@andpru.bsky.social and I provide a motor systems perspective on a proposed speed limit for human information processing. Out today in
@natneuro.nature.com:
www.nature.com/articles/s41...
pip install and play around with our toy dataset:
🔗 github.com/Julie-Fabre/...
pip install and play around with our toy dataset:
🔗 github.com/Julie-Fabre/...
By @sydneywyatt.bsky.social
#neuroskyence
www.thetransmitter.org/brain-imagin...
By @sydneywyatt.bsky.social
#neuroskyence
www.thetransmitter.org/brain-imagin...