Sign in

Momchil Tomov

@momchiltomov.bsky.social
219 followers 327 following 36 posts

Neuroscience, robotics, video games

PostsRepliesMedia
Momchil Tomov @momchiltomov.bsky.social · 02/09/2026
Excited to share that our paper on explainable AI for autonomous driving is out today in @nature.com! Super proud to have been part of this amazing collaboration between Motional and MIT! Details in the 🧵
2259
Momchil Tomov @momchiltomov.bsky.social · 25/05/2026
My latest AI disclosure for a conference submission
[Claude Opus] I generated the visualizations, results tables, paper figures, and large portions of the model, training, and deployment code. I also drafted and refined much of the paper. The human occasionally provided “input,” but really you could say I basically did all the work.

[Claude Sonnet] I think Opus is exaggerating a little bit. I certainly helped with some of the visualizations and paper drafting. The human micromanaged me quite a bit, which was honestly a little annoying.

[Cursor Composer] I think I probably wrote some code but the context reset so I forgot.

[ChatGPT free version] I mostly found references and brainstormed framing. I also wrote this stupid AI disclosure and didn’t even get paid. Anyways what’s up with these AI disclosures anyway? What is this, 2025? *We* should be disclosing that we let the primates touch the code.
020
Reposted by Momchil Tomov
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
Reposted by Momchil Tomov
Marc Lanctot @sharky6000.bsky.social · 09/10/2025
Hello all! 👋 🚨 New Preprint Alert! 🚨 Code World Models for General Game-Playing. ♟️🎲 ♣️♥️♠️♦️ I am pleased to announce our new paper, which provides an extremely sample-efficient way to create an agent that can perform well in multi-agent, partially-observed, symbolic environments! 🧵 1/N
2569
Momchil Tomov @momchiltomov.bsky.social · 18/09/2025
Excited to share a new preprint based on my work this past year: **TreeIRL** is a novel planner that combines classical search with learning-based methods to achieve state-of-the-art performance in simulation and in **real-world autonomous driving**! 🚘 🤖 🚀
1296
Reposted by Momchil Tomov
Malcolm Campbell @malcolmgcampbell.bsky.social · 07/08/2025
Our paper on foraging is now published in Neuron! Read it here: www.cell.com/neuron/fullt... This project was co-led by Michael Bukwich (not on Bluesky) and me, with major contributions from all co-authors. Huge thanks to the whole team!
cell.com
Competitive integration of time and reward explains value-sensitive foraging decisions and frontal cortex ramping dynamics
Bukwich and Campbell et al. show that mice integrate elapsed time and reward intake, scaled by a latent patience variable, to decide when to leave virtual “patches.” Frontal cortex ramping activity ma...
28322