Taco Cohen
@taco-cohen.bsky.social
Deep learner at FAIR. Into codegen, RL, equivariance, generative models. Spent time at Qualcomm, Scyfer (acquired), UvA, Deepmind, OpenAI.
Reposted by Taco Cohen
4yrs ago, the Geometric Deep Learning proto-book hit the arXiv 📚
Today, we proudly release *Chapter 4* of the GDL Book! 📖 Wrapping up foundations, exceeding the proto-book page count 🚀
Next: deep-dives into the 5 Gs! #⃣🔁🕸️🌐🪢
@mmbronstein.bsky.social @joanbruna.bsky.social @taco-cohen.bsky.social
Today, we proudly release *Chapter 4* of the GDL Book! 📖 Wrapping up foundations, exceeding the proto-book page count 🚀
Next: deep-dives into the 5 Gs! #⃣🔁🕸️🌐🪢
@mmbronstein.bsky.social @joanbruna.bsky.social @taco-cohen.bsky.social
April 29, 2025 at 12:01 AM
4yrs ago, the Geometric Deep Learning proto-book hit the arXiv 📚
Today, we proudly release *Chapter 4* of the GDL Book! 📖 Wrapping up foundations, exceeding the proto-book page count 🚀
Next: deep-dives into the 5 Gs! #⃣🔁🕸️🌐🪢
@mmbronstein.bsky.social @joanbruna.bsky.social @taco-cohen.bsky.social
Today, we proudly release *Chapter 4* of the GDL Book! 📖 Wrapping up foundations, exceeding the proto-book page count 🚀
Next: deep-dives into the 5 Gs! #⃣🔁🕸️🌐🪢
@mmbronstein.bsky.social @joanbruna.bsky.social @taco-cohen.bsky.social
Reposted by Taco Cohen
Congrats to Dr. @phillip-lippe.bsky.social for receiving a "cum laude" PhD at the University of Amsterdam for his work on #causal representation learning 🎉 @ellisamsterdam.bsky.social
It was a pleasure to cosupervise you with
@egavves.bsky.social @yukimasano.bsky.social @taco-cohen.bsky.social
It was a pleasure to cosupervise you with
@egavves.bsky.social @yukimasano.bsky.social @taco-cohen.bsky.social
February 27, 2025 at 8:09 PM
Congrats to Dr. @phillip-lippe.bsky.social for receiving a "cum laude" PhD at the University of Amsterdam for his work on #causal representation learning 🎉 @ellisamsterdam.bsky.social
It was a pleasure to cosupervise you with
@egavves.bsky.social @yukimasano.bsky.social @taco-cohen.bsky.social
It was a pleasure to cosupervise you with
@egavves.bsky.social @yukimasano.bsky.social @taco-cohen.bsky.social
Evidence is accumulating that when implemented well, equivariant nets improve scalability / compute efficiency!
Common beliefs about equivariant networks for image input include 1) They are slow. 2) They don’t scale to ImageNet. 3) They are complicated. In my opinion, these three are all false. To argue against them, we made minimal modifications to popular vision models, turning them mirror-equivariant.
February 10, 2025 at 12:48 PM
Evidence is accumulating that when implemented well, equivariant nets improve scalability / compute efficiency!
Reposted by Taco Cohen
Griffin Scholars (very smart Ukrainian undergraduates from top unis) are looking for research internships in maths or CS.
(many of them can't return to Ukraine for the summer).
If you can host them (we may help with funding), please fill out this form:
ferenchuszar1.typeform.com/to/WjXursg3
(many of them can't return to Ukraine for the summer).
If you can host them (we may help with funding), please fill out this form:
ferenchuszar1.typeform.com/to/WjXursg3
December 12, 2024 at 3:12 PM
Griffin Scholars (very smart Ukrainian undergraduates from top unis) are looking for research internships in maths or CS.
(many of them can't return to Ukraine for the summer).
If you can host them (we may help with funding), please fill out this form:
ferenchuszar1.typeform.com/to/WjXursg3
(many of them can't return to Ukraine for the summer).
If you can host them (we may help with funding), please fill out this form:
ferenchuszar1.typeform.com/to/WjXursg3
Reposted by Taco Cohen
Just arrived in Vancouver for #NeurIPS.
I'm looking forward to meeting old and new friends, learning a thing or two, and presenting some recent work:
1/6
I'm looking forward to meeting old and new friends, learning a thing or two, and presenting some recent work:
1/6
December 11, 2024 at 5:15 AM
Just arrived in Vancouver for #NeurIPS.
I'm looking forward to meeting old and new friends, learning a thing or two, and presenting some recent work:
1/6
I'm looking forward to meeting old and new friends, learning a thing or two, and presenting some recent work:
1/6
On my way to NeurIPS! Looking forward to meeting old friends and making new ones. LMK if you're into codegen and RL and want to chat!
December 8, 2024 at 10:15 AM
On my way to NeurIPS! Looking forward to meeting old friends and making new ones. LMK if you're into codegen and RL and want to chat!