https://psc-g.github.io/
open.spotify.com/album/0Eb3vq...
We'll do one last tomorrow, same place, same time, for those who are still around.
We'll do one last tomorrow, same place, same time, for those who are still around.
#rlconference #RLC2026
maps.app.goo.gl/UoqpDjGgQDch...
#rlconference #RLC2026
maps.app.goo.gl/UoqpDjGgQDch...
See you there!
maps.app.goo.gl/w7e7CqRbARdG...
See you there!
maps.app.goo.gl/w7e7CqRbARdG...
Looking forward to moderating this debate!
Looking forward to moderating this debate!
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
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
Come chat with me and @caroline-wang.bsky.social this Thursday afternoon, 5pm, #ICML2026 poster session in Hall A (Poster #401)!
TLDR: We used LLM-powered program synthesis to automatically model and discover differences between human and LLM strategic behavior
Come chat with me and @caroline-wang.bsky.social this Thursday afternoon, 5pm, #ICML2026 poster session in Hall A (Poster #401)!
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
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
Join us tomorrow, same place and same time!
Join us tomorrow, same place and same time!
Come chat with us about good representations for RL!
#ICML2026
"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 👇
Come chat with us about good representations for RL!
#ICML2026
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!
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!
Join us tomorrow, same place, same time!
Join us tomorrow, same place, same time!
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
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
In this work, we revisit a fundamental question in reinforcement learning:
What if representation learning was the key ingredient behind scalable RL?
1/🧵
In this work, we revisit a fundamental question in reinforcement learning:
What if representation learning was the key ingredient behind scalable RL?
1/🧵
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!
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...
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!
also passed some lifeguards in training during my last sprint
also passed some lifeguards in training during my last sprint
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...
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...
🗓️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!
TLDR: We used LLM-powered program synthesis to automatically model and discover differences between human and LLM strategic behavior
🗓️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!
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
In our recent preprint we demonstrate that the use of well-structured representations (SEMs) can dramatically improve sample efficiency in RL agents.
1/X
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