lennertds.bsky.social

24 February 2026 12:22

If you care about enforcing constraints over time without breaking your computational resources, then read our new blog post over at @aihub.org! It focuses on showing how our neurosymbolic Markov models beat the SOTA in out-of-distribution generalisation and so much more.

RL and Video Games Workshop

rlvgworkshop.bsky.social

29 July 2025 17:55

We’re excited to announce our final keynote speaker: @michaelhbowling.bsky.social (University of Alberta). 🎲🃏 In this talk, he will explore what drew him to explore using 40-year-old video games to test RL agents! Join us at @rl-conference.bsky.social to find out more about the Atari Benchmark!

Jaron Maene

jjcmoon.bsky.social

23 April 2025 13:00

We developed a library to make logical reasoning embarrasingly parallel on the GPU. For those at ICLR 🇸🇬: you can get the juicy details tomorrow (poster #414 at 15:00). Hope to see you there!

Pedro Zuidberg Dos Martires

pedrozudo.bsky.social

22 April 2025 12:13

What is reasoning and have LLMs learned it? We answer these two questions in our new pre-print using the phase transition in random 3-SAT. arxiv.org/abs/2504.039... Together with @rishihazra95.bsky.social, @gabventurato.bsky.social and @lucderaedt.bsky.social Here is also a longer thread:

Gary Marcus

garymarcus.bsky.social

10 March 2025 12:08

Covid killed > 7M people, confirmed, and likely over 20M (“excess death”s). Would have been a lot more without PPEs & vaccines. Putin has annexed Crimea, invaded Ukraine, plus conflicts in Georgia and Syria; would have been a lot more without NATO. This is not the analogy David Sacks thinks it is.