Sign in

Botos Csabi

@botoscsabi.bsky.social
43 followers 46 following 5 posts

Fresh DPhil from @oxfordtvg.bsky.social Working on low-latency/low-resource AI Neuroscience wannabe botcs.github.io

PostsRepliesMedia
Botos Csabi @botoscsabi.bsky.social · 11/05/2026
My rockstar team: @sreejan.bsky.social , Austin Andrews, @lhuntneuro.bsky.social @summerfieldlab.bsky.social @joshtenenbaum.bsky.social @somnirons.bsky.social @marcelomattar.bsky.social and the brilliant @momchiltomov.bsky.social The project was funded by: encode.pillar.vc
040
Botos Csabi @botoscsabi.bsky.social · 11/05/2026
Jeee 🐦‍⬛ I am very proud of our joint effort with @sreejan.bsky.social on the project "Reason to Play" LRMs show human-like rule discovery, and their hidden states predict human brain activity during gameplay 10x better than previous methods Interactive demo + paper: botcs.github.io/reason-to-pl...
botcs.github.io
Reason to Play - Behavioral and Brain Alignment
32 fMRI-scanned humans and 8 frontier open weight LLMs play ARC-AGI like games with no rules given. The reasoning models match the human learning trajectories and their hidden states predict human bra...
13911
Botos Csabi @botoscsabi.bsky.social · 08/12/2024
that was my first guess as well, but that only works with identical indices between source and target. if the max(K):T ratio is low then I guess it worths 1) gathering into an intermediate tensor 2) shuffling the values 3) scattering to x`.
010
Botos Csabi @botoscsabi.bsky.social · 08/12/2024
I think the best solution really depends on the ratios 1) max(K):T 2) N:D. since K can vary for different {n}s I would start with - find the largest K and allocate x`=torch.zeros(N, max_K+1, D) - iterate over N - create a src index [0, t_1 .. t_K] and trg [t_1, .., T-1] - x`[n, src, :]=v[n, trg, :]
110
Botos Csabi @botoscsabi.bsky.social · 08/12/2024
Yay 🦜 Heading to Vancouver on Monday to present my first ever @neuripsconf.bsky.social paper. I am super duper excited to finally join the cool kids’ gang. Check out the tutorial I procrastinated over for 3 months: youtu.be/EbPrlGkLxGo
youtu.be
[Demo] Label Delay for Online Continual Learning
YouTube video by Csaba Botos
020