Pablo Samuel Castro
banner
pcastr.bsky.social
Pablo Samuel Castro
@pcastr.bsky.social
Señor swesearcher @ Google DeepMind, adjunct prof at Université de Montréal and Mila. Musician. From 🇪🇨 living in 🇨🇦.
https://psc-g.github.io/
Pinned
thrilled to finally put out the second release from my musical project "the 45s" with my buddy JS Diallo!

open.spotify.com/album/0Eb3vq...
Third #runconference at #RLC2026 going strong!
We'll do one last tomorrow, same place, same time, for those who are still around.
August 18, 2026 at 1:54 PM
Another great #runconference at #RLC2026 !
Same place, same time tomorrow!
August 17, 2026 at 5:10 PM
If you're closer to the venue, Josiah will be starting at 7 right in front of the conference venue
#rlconference #RLC2026
maps.app.goo.gl/UoqpDjGgQDch...
August 16, 2026 at 10:41 PM
Great turnout for our first #runconference at #RLC2026 !
Same place, same time tomorrow!
August 16, 2026 at 7:05 PM
Great talk by Marc G. Bellemare at #RLC2026 , ranging from deep RL representations, to stable LLM post-training, to robust statistical measures of performance!
August 16, 2026 at 2:35 PM
At #RLC2026 and want to run? Come for a #runconference tomorrow (Sunday)! Let's meet at 7am at the pin below and run up the mountain for a beautiful morning view.

See you there!

maps.app.goo.gl/w7e7CqRbARdG...
August 15, 2026 at 8:15 PM
If you're at #RLC2026, come by, starting in 15ish minutes! I'm currently making my way from the airport but should arrive just in the nick of time 😅
Looking forward to moderating this debate!
August 15, 2026 at 5:44 PM
Fifth and last #runconference at #ICML2026 was great! Thanks to everyone who came out, and until next time!
July 11, 2026 at 1:11 AM
in workshops, when panels start, i leave.
July 10, 2026 at 9:05 AM
Fourth #runconference at #ICML2026 was a bit of a bust, as separate running club cancelled last minute 🫤
Still had a nice (and very humid) solo run.
Tomorrow will be the last one, we'll meet at 8am at Hannam station for a run around the river, join us!
naver.me/F5swAa7n
July 10, 2026 at 7:00 AM
Interested in the differences in strategic behavior between humans and LLMs?
Come chat with me and @caroline-wang.bsky.social this Thursday afternoon, 5pm, #ICML2026 poster session in Hall A (Poster #401)!
[1/n] Just wrapped up 7 months interning with @pcastr.bsky.social at Google DeepMind and I'm so excited to share our work: arxiv.org/abs/2602.10324.

TLDR: We used LLM-powered program synthesis to automatically model and discover differences between human and LLM strategic behavior
July 9, 2026 at 4:28 AM
No rain for third #runconference at #ICML2026 but it was quite humid!
Tomorrow we'll join a separate running club at 8am, running around some of the main sights in Seoul, join us!
Apparently anyone can join, just register here:
luma.com/o0wqzdyc
July 9, 2026 at 1:41 AM
Second #runconference at #ICML2026 was *very* wet, but we did it!
Join us tomorrow, same place and same time!
July 8, 2026 at 8:26 AM
Today I'll be presenting this spotlight poster with Ali at 2:30-4:15, in Hall A, poster #303.
Come chat with us about good representations for RL!
#ICML2026
New paper 🚨
"Stable Deep Reinforcement Learning via Isotropic Gaussian Representations"

Deep RL suffers from unstable training, representation collapse, and neuron dormancy. We show that a simple geometric insight, isotropic Gaussian representations, can fix this. Here's how 👇
July 8, 2026 at 2:07 AM
At the Google booth until 11. Stop by!
#icml2026
July 8, 2026 at 1:13 AM
Today at the #ICML2026 LatinX in AI workshop Ali did a great job presenting our paper!
We'll be presenting the poster at the main conference, tomorrow Wednesday July 8th, 2:30-4:15, Hall A, poster #303.
Come chat with Ali and me then!
July 7, 2026 at 5:10 AM
First #runconference at #ICML2026 was rainy but good! We ran up to the city wall and got nice views of the city.
Join us tomorrow, same place, same time!
July 7, 2026 at 4:07 AM
At Seoul for #ICML2026 and want to start your days with a run?
Meet me tomorrow Tuesday at 7am in front of COCODA

[NAVER Maps]
COCODA
398-6 Jongno 5(o)-ga Jongno-gu Seoul
naver.me/xuFb2ppi

#runconference
July 6, 2026 at 12:14 AM
I'm excited to share our latest work “Representation Learning Enables Scalable Multitask Deep Reinforcement Learning”.
In this work, we revisit a fundamental question in reinforcement learning:
What if representation learning was the key ingredient behind scalable RL?
1/🧵
July 1, 2026 at 1:30 PM
really proud of this work done with fantastic collaborators, in particular daniel, @kevinjmiller.bsky.social & @neurokim.bsky.social !
i learned so much about neuroscience, & it was great to work on using AI techniques to advance science.
read kevin's thread below or, even better, read the paper!
Computational models are a key part of science but discovering new ones is hard!

DataDIVER discovers concise models from data, which surface new mechanistic ideas and clear predictions for future experiments

From Google Deepmind Neuroscience Lab + collaborators

www.biorxiv.org/content/10.6...
June 4, 2026 at 9:11 PM
I wish there were a way to increase diversity in workshop keynotes/panelists. There are a few famous researchers who end up being keynotes/panelists on multiple workshops, which means lots of other great researchers are not getting those opportunities.
April 29, 2026 at 8:57 AM
Fun last #runconference at #ICLR2026, included sidewalk and beach running, a little soccer ball kicking, and going in the Ocean!
also passed some lifeguards in training during my last sprint
April 27, 2026 at 12:04 PM
Another great #runconference this morning at #ICLR2026 !
Tomorrow is my last day so trying something different:
BEACH RUN
Let's meet at the pin below at 7:30am, run for a bit, then go in the water for a swim!
maps.app.goo.gl/KZfuFtgsdmn4...
April 26, 2026 at 8:16 PM
I will be giving a talk about this work at the "From Human Cognition to AI Reasoning: Models, Methods, and Applications" #ICLR2026 workshop

🗓️Sunday, April 26, 2026 10:30 AM BRT
📍 Room 202 C

As well as a poster at 3:30pm in the same room.

Come by!
[1/n] Just wrapped up 7 months interning with @pcastr.bsky.social at Google DeepMind and I'm so excited to share our work: arxiv.org/abs/2602.10324.

TLDR: We used LLM-powered program synthesis to automatically model and discover differences between human and LLM strategic behavior
April 26, 2026 at 9:57 AM
Still at #ICLR2026 and still into RL?
Come talk to @johanobandoc.bsky.social @waltermayor.bsky.social and me at our poster today (Saturday)!
🗓️April 25, 3:15 PM -5:45 PM BRT
📍Pavilion 4·
#️⃣ Poster #4515
🔊Simplicial Embeddings (SEMs) Improve Sample Efficiency in Actor-Critic Agents🔊

In our recent preprint we demonstrate that the use of well-structured representations (SEMs) can dramatically improve sample efficiency in RL agents.

1/X
April 25, 2026 at 5:46 PM