Mandana Samiei
@mandanas.bsky.social
PhD candidate at McGill and Mila (Quebec AI Institute) w/ Blake Richards and Doina Precup.
Doing research on AI and Neuroscience 🤖🧠
Based in Montreal. 🇨🇦
Doing research on AI and Neuroscience 🤖🧠
Based in Montreal. 🇨🇦
Huge congratulations! Already looking forward to the breakthroughs you'll lead!
Thrilled to announce I'll be starting my own neuro-theory lab, as an Assistant Professor at @yaleneuro.bsky.social @wutsaiyale.bsky.social this Fall!
My group will study offline learning in the sleeping brain: how neural activity self-organizes during sleep and the computations it performs. 🧵
My group will study offline learning in the sleeping brain: how neural activity self-organizes during sleep and the computations it performs. 🧵
June 30, 2025 at 6:13 PM
Huge congratulations! Already looking forward to the breakthroughs you'll lead!
Great deep dive into hierarchical reinforcement learning, essential reading for anyone exploring scalable, structured agents. Shoutout to the authors!
As AI agents face increasingly long and complex tasks, decomposing them into subtasks becomes increasingly appealing.
But how do we discover such temporal structure?
Hierarchical RL provides a natural formalism-yet many questions remain open.
Here's our overview of the field🧵
But how do we discover such temporal structure?
Hierarchical RL provides a natural formalism-yet many questions remain open.
Here's our overview of the field🧵
June 30, 2025 at 4:27 PM
Great deep dive into hierarchical reinforcement learning, essential reading for anyone exploring scalable, structured agents. Shoutout to the authors!
Reposted by Mandana Samiei
Our work with Pablo Tano, @hyunggoo-kim.bsky.social Athar Malik, Alexandre Pouget and @naoshigeuchida.bsky.social exploring how dopamine neurons could enable multi-timescale reinforcement learning in the brain is out in @nature.com
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Multi-timescale reinforcement learning in the brain - Nature
Individual dopaminergic neurons encode future rewards over distinct temporal horizons.
www.nature.com
June 4, 2025 at 6:11 PM
Our work with Pablo Tano, @hyunggoo-kim.bsky.social Athar Malik, Alexandre Pouget and @naoshigeuchida.bsky.social exploring how dopamine neurons could enable multi-timescale reinforcement learning in the brain is out in @nature.com
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Many LMs default to disjunctive inferences—even when given conjunctive evidence. Unlike children, LMs’ exploration is shaped by the underlying causal rule.
Could promoting child-like curiosity help LMs reason more effectively about causality?
More details: arxiv.org/abs/2505.09614
Could promoting child-like curiosity help LMs reason more effectively about causality?
More details: arxiv.org/abs/2505.09614
May 16, 2025 at 9:04 PM
Many LMs default to disjunctive inferences—even when given conjunctive evidence. Unlike children, LMs’ exploration is shaped by the underlying causal rule.
Could promoting child-like curiosity help LMs reason more effectively about causality?
More details: arxiv.org/abs/2505.09614
Could promoting child-like curiosity help LMs reason more effectively about causality?
More details: arxiv.org/abs/2505.09614
A great collab with former labmates @agx-chen.bsky.social & @dongyanl1n.bsky.social.
Interesting limitation in LMs: strong disjunctive bias leads to poor performance on conjunctive causal inference tasks. Mirrors adult human biases--possibly a byproduct of training data prior.
Interesting limitation in LMs: strong disjunctive bias leads to poor performance on conjunctive causal inference tasks. Mirrors adult human biases--possibly a byproduct of training data prior.
Language model (LM) agents are all the rage now—but they may exhibit cognitive biases when inferring causal relationships!
We evaluate LMs on a cognitive task to find:
- LMs struggle with certain simple causal relationships
- They show biases similar to human adults (but not children)
🧵⬇️
We evaluate LMs on a cognitive task to find:
- LMs struggle with certain simple causal relationships
- They show biases similar to human adults (but not children)
🧵⬇️
May 16, 2025 at 8:51 PM
A great collab with former labmates @agx-chen.bsky.social & @dongyanl1n.bsky.social.
Interesting limitation in LMs: strong disjunctive bias leads to poor performance on conjunctive causal inference tasks. Mirrors adult human biases--possibly a byproduct of training data prior.
Interesting limitation in LMs: strong disjunctive bias leads to poor performance on conjunctive causal inference tasks. Mirrors adult human biases--possibly a byproduct of training data prior.
Reposted by Mandana Samiei
Just over a week since I defended my 🤖+🧠PhD thesis, and the feeling is just sinking in. Extremely grateful to
@tyrellturing.bsky.social for supporting me through this amazing journey! 🙏
Big thanks to all members of the LiNC lab, and colleagues at mcgill University and @mila-quebec.bsky.social. ❤️😁
@tyrellturing.bsky.social for supporting me through this amazing journey! 🙏
Big thanks to all members of the LiNC lab, and colleagues at mcgill University and @mila-quebec.bsky.social. ❤️😁
February 10, 2025 at 12:36 PM
Just over a week since I defended my 🤖+🧠PhD thesis, and the feeling is just sinking in. Extremely grateful to
@tyrellturing.bsky.social for supporting me through this amazing journey! 🙏
Big thanks to all members of the LiNC lab, and colleagues at mcgill University and @mila-quebec.bsky.social. ❤️😁
@tyrellturing.bsky.social for supporting me through this amazing journey! 🙏
Big thanks to all members of the LiNC lab, and colleagues at mcgill University and @mila-quebec.bsky.social. ❤️😁
Reposted by Mandana Samiei
The slides of my NeurIPS lecture "From Diffusion Models to Schrödinger Bridges - Generative Modeling meets Optimal Transport" can be found here
drive.google.com/file/d/1eLa3...
drive.google.com/file/d/1eLa3...
BreimanLectureNeurIPS2024_Doucet.pdf
drive.google.com
December 15, 2024 at 6:40 PM
The slides of my NeurIPS lecture "From Diffusion Models to Schrödinger Bridges - Generative Modeling meets Optimal Transport" can be found here
drive.google.com/file/d/1eLa3...
drive.google.com/file/d/1eLa3...
Reposted by Mandana Samiei
I gave a talk on Compositional World Models at NeurIPS last week 🌐
The recording is now online: neurips.cc/virtual/2024... (for registered attendees; starts at 6:06:00)
Workshop: compositional-learning.github.io
The recording is now online: neurips.cc/virtual/2024... (for registered attendees; starts at 6:06:00)
Workshop: compositional-learning.github.io
December 19, 2024 at 1:57 AM
I gave a talk on Compositional World Models at NeurIPS last week 🌐
The recording is now online: neurips.cc/virtual/2024... (for registered attendees; starts at 6:06:00)
Workshop: compositional-learning.github.io
The recording is now online: neurips.cc/virtual/2024... (for registered attendees; starts at 6:06:00)
Workshop: compositional-learning.github.io
Reposted by Mandana Samiei
🔊 Super excited to announce the first ever Frontiers of Probabilistic Inference: Learning meets Sampling workshop at #ICLR2025 @iclr-conf.bsky.social!
🔗 website: sites.google.com/view/fpiwork...
🔥 Call for papers: sites.google.com/view/fpiwork...
more details in thread below👇 🧵
🔗 website: sites.google.com/view/fpiwork...
🔥 Call for papers: sites.google.com/view/fpiwork...
more details in thread below👇 🧵
December 18, 2024 at 7:09 PM
🔊 Super excited to announce the first ever Frontiers of Probabilistic Inference: Learning meets Sampling workshop at #ICLR2025 @iclr-conf.bsky.social!
🔗 website: sites.google.com/view/fpiwork...
🔥 Call for papers: sites.google.com/view/fpiwork...
more details in thread below👇 🧵
🔗 website: sites.google.com/view/fpiwork...
🔥 Call for papers: sites.google.com/view/fpiwork...
more details in thread below👇 🧵
Reposted by Mandana Samiei
If you review for a #ML conference like @iclr-conf.bsky.social or @neuripsconf.bsky.social, YOU HAVE A RESPONSIBILITY TO REPLY TO THE AUTHORS.
If the rebuttal doesn't address your concerns explain why. But giving a score of 2-3 then ghosting the authors is super rude.
I say this as an AC.
#MLSky
If the rebuttal doesn't address your concerns explain why. But giving a score of 2-3 then ghosting the authors is super rude.
I say this as an AC.
#MLSky
December 4, 2024 at 10:58 PM
If you review for a #ML conference like @iclr-conf.bsky.social or @neuripsconf.bsky.social, YOU HAVE A RESPONSIBILITY TO REPLY TO THE AUTHORS.
If the rebuttal doesn't address your concerns explain why. But giving a score of 2-3 then ghosting the authors is super rude.
I say this as an AC.
#MLSky
If the rebuttal doesn't address your concerns explain why. But giving a score of 2-3 then ghosting the authors is super rude.
I say this as an AC.
#MLSky
Reposted by Mandana Samiei
Now that @jeffclune.bsky.social and @joelbot3000.bsky.social are here, time for an Open-Endedness starter pack.
go.bsky.app/MdVxrtD
go.bsky.app/MdVxrtD
November 20, 2024 at 7:08 AM
Now that @jeffclune.bsky.social and @joelbot3000.bsky.social are here, time for an Open-Endedness starter pack.
go.bsky.app/MdVxrtD
go.bsky.app/MdVxrtD
Reposted by Mandana Samiei
4/ I think the proper definition is that #NeuroAI is the realization of the original promise of cybernetics and connectionism!
en.wikipedia.org/wiki/Cyberne...
en.wikipedia.org/wiki/Connect...
It is a general science of intelligence focussed on parallel distributed systems, control, and learning.
en.wikipedia.org/wiki/Cyberne...
en.wikipedia.org/wiki/Connect...
It is a general science of intelligence focussed on parallel distributed systems, control, and learning.
November 21, 2024 at 4:20 PM
4/ I think the proper definition is that #NeuroAI is the realization of the original promise of cybernetics and connectionism!
en.wikipedia.org/wiki/Cyberne...
en.wikipedia.org/wiki/Connect...
It is a general science of intelligence focussed on parallel distributed systems, control, and learning.
en.wikipedia.org/wiki/Cyberne...
en.wikipedia.org/wiki/Connect...
It is a general science of intelligence focussed on parallel distributed systems, control, and learning.
Reposted by Mandana Samiei
1/ I work in #NeuroAI, a growing field of research, which many people have only the haziest conception of...
As way of introduction to this research approach, I'll provide here a very short thread outlining the definition of the field I gave recently at our BRAIN NeuroAI workshop at the NIH.
🧠📈
As way of introduction to this research approach, I'll provide here a very short thread outlining the definition of the field I gave recently at our BRAIN NeuroAI workshop at the NIH.
🧠📈
November 21, 2024 at 4:20 PM
1/ I work in #NeuroAI, a growing field of research, which many people have only the haziest conception of...
As way of introduction to this research approach, I'll provide here a very short thread outlining the definition of the field I gave recently at our BRAIN NeuroAI workshop at the NIH.
🧠📈
As way of introduction to this research approach, I'll provide here a very short thread outlining the definition of the field I gave recently at our BRAIN NeuroAI workshop at the NIH.
🧠📈
Reposted by Mandana Samiei
I wish that I was able to convince the students in my class that the ultimate goal of science isn't accumulation of facts but the compression of facts into theories. Mel summarizes it well here:
www.nature.com/articles/nn1...
Unfortunately, I think this is a minority viewpoint within neuroscience.
www.nature.com/articles/nn1...
Unfortunately, I think this is a minority viewpoint within neuroscience.
www.nature.com
November 12, 2024 at 12:07 PM
I wish that I was able to convince the students in my class that the ultimate goal of science isn't accumulation of facts but the compression of facts into theories. Mel summarizes it well here:
www.nature.com/articles/nn1...
Unfortunately, I think this is a minority viewpoint within neuroscience.
www.nature.com/articles/nn1...
Unfortunately, I think this is a minority viewpoint within neuroscience.