Ramy Mounir
@ramymounir.com
AI Researcher @ Thousand Brains Project
Reposted by Ramy Mounir
We took Monty off the simulator and into the real world.
3 teams, 1 intense week:
🧱 Lego + RaspberryPi
🧠 Monty-guided ultrasound
🛸 Drone vision system
🎥 Watch the video: youtu.be/5UcoyF_ws9s
📖 Event recap: thousandbrains.org/2025-05-robo...
3 teams, 1 intense week:
🧱 Lego + RaspberryPi
🧠 Monty-guided ultrasound
🛸 Drone vision system
🎥 Watch the video: youtu.be/5UcoyF_ws9s
📖 Event recap: thousandbrains.org/2025-05-robo...
2025/05 - Robot Hackathon Presentations
YouTube video by Thousand Brains Project
youtu.be
August 7, 2025 at 7:53 PM
We took Monty off the simulator and into the real world.
3 teams, 1 intense week:
🧱 Lego + RaspberryPi
🧠 Monty-guided ultrasound
🛸 Drone vision system
🎥 Watch the video: youtu.be/5UcoyF_ws9s
📖 Event recap: thousandbrains.org/2025-05-robo...
3 teams, 1 intense week:
🧱 Lego + RaspberryPi
🧠 Monty-guided ultrasound
🛸 Drone vision system
🎥 Watch the video: youtu.be/5UcoyF_ws9s
📖 Event recap: thousandbrains.org/2025-05-robo...
Reposted by Ramy Mounir
1/
🚨Another New Paper Drop! 🚨 “Hierarchy or Heterarchy? A Theory of Long-Range Connections for the Sensorimotor Brain”
👇 Dive into the full thread 🧵
arxiv.org/abs/2507.05888
🚨Another New Paper Drop! 🚨 “Hierarchy or Heterarchy? A Theory of Long-Range Connections for the Sensorimotor Brain”
👇 Dive into the full thread 🧵
arxiv.org/abs/2507.05888
July 11, 2025 at 6:35 PM
1/
🚨Another New Paper Drop! 🚨 “Hierarchy or Heterarchy? A Theory of Long-Range Connections for the Sensorimotor Brain”
👇 Dive into the full thread 🧵
arxiv.org/abs/2507.05888
🚨Another New Paper Drop! 🚨 “Hierarchy or Heterarchy? A Theory of Long-Range Connections for the Sensorimotor Brain”
👇 Dive into the full thread 🧵
arxiv.org/abs/2507.05888
Reposted by Ramy Mounir
/1
🚨 New Paper Drop 🚨
We’ve released “Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning & Inference” — the first working implementation of a thousand-brains system, code-named Monty.
👇 Dive into the full thread 🧵
arxiv.org/abs/2507.04494
🚨 New Paper Drop 🚨
We’ve released “Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning & Inference” — the first working implementation of a thousand-brains system, code-named Monty.
👇 Dive into the full thread 🧵
arxiv.org/abs/2507.04494
July 9, 2025 at 9:02 PM
/1
🚨 New Paper Drop 🚨
We’ve released “Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning & Inference” — the first working implementation of a thousand-brains system, code-named Monty.
👇 Dive into the full thread 🧵
arxiv.org/abs/2507.04494
🚨 New Paper Drop 🚨
We’ve released “Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning & Inference” — the first working implementation of a thousand-brains system, code-named Monty.
👇 Dive into the full thread 🧵
arxiv.org/abs/2507.04494
Reposted by Ramy Mounir
Ok this is one I've been really excited to share - our pre-print demonstrating the capabilities of thousand-brain systems is now out 🧠🚀 It gives a great overview of why we believe the approach we're taking is so promising. Rapid and continual learning leading to rapid and...
1/
This week, we’re releasing two milestone papers: one shows the amazing capabilities of thousand-brains systems and their benefits over deep learning, the other proposes a new theory of long-range connections in the neocortex. Years of work led to this.
This week, we’re releasing two milestone papers: one shows the amazing capabilities of thousand-brains systems and their benefits over deep learning, the other proposes a new theory of long-range connections in the neocortex. Years of work led to this.
July 8, 2025 at 2:02 PM
Ok this is one I've been really excited to share - our pre-print demonstrating the capabilities of thousand-brain systems is now out 🧠🚀 It gives a great overview of why we believe the approach we're taking is so promising. Rapid and continual learning leading to rapid and...
This is a big deal! When continual learning, robustness to noise, high accuracy, and efficiency all emerge naturally from a single system inspired by the neocortex, you know you're onto something powerful!
Niels and Viviane's video explainers are an absolute must-watch!
Niels and Viviane's video explainers are an absolute must-watch!
1/
This week, we’re releasing two milestone papers: one shows the amazing capabilities of thousand-brains systems and their benefits over deep learning, the other proposes a new theory of long-range connections in the neocortex. Years of work led to this.
This week, we’re releasing two milestone papers: one shows the amazing capabilities of thousand-brains systems and their benefits over deep learning, the other proposes a new theory of long-range connections in the neocortex. Years of work led to this.
July 9, 2025 at 1:04 AM
This is a big deal! When continual learning, robustness to noise, high accuracy, and efficiency all emerge naturally from a single system inspired by the neocortex, you know you're onto something powerful!
Niels and Viviane's video explainers are an absolute must-watch!
Niels and Viviane's video explainers are an absolute must-watch!
Reposted by Ramy Mounir
@canoetrip.bsky.social, @ramymounir.com, and @hojaeklee.bsky.social recap early thinking on behavior modeling in the context of the Thousand Brains Theory 🧠
Each explores a different angle, aiming to map the current landscape and open questions 🧭
Video:
youtu.be/EvRkfL1rczM
Each explores a different angle, aiming to map the current landscape and open questions 🧭
Video:
youtu.be/EvRkfL1rczM
2025/05 - Scott, Ramy and Hojae Review Behavior Progress
YouTube video by Thousand Brains Project
youtu.be
June 10, 2025 at 9:09 PM
@canoetrip.bsky.social, @ramymounir.com, and @hojaeklee.bsky.social recap early thinking on behavior modeling in the context of the Thousand Brains Theory 🧠
Each explores a different angle, aiming to map the current landscape and open questions 🧭
Video:
youtu.be/EvRkfL1rczM
Each explores a different angle, aiming to map the current landscape and open questions 🧭
Video:
youtu.be/EvRkfL1rczM