Dane Carnegie Malenfant
@dvnxmvlhdf5.bsky.social
MSc. @mila-quebec.bsky.social and @mcgill.ca in the LiNC lab
Fixating on multi-agent RL, Neuro-AI and decisions
Ēka ē-akimiht
https://danemalenfant.com/
Fixating on multi-agent RL, Neuro-AI and decisions
Ēka ē-akimiht
https://danemalenfant.com/
Pinned
Preprint Alert 🚀
Multi-agent reinforcement learning (MARL) often assumes that agents know when other agents cooperate with them. But for humans, this isn’t always the case. For example, plains indigenous groups used to leave resources for others to use at effigies called Manitokan.
1/8
Multi-agent reinforcement learning (MARL) often assumes that agents know when other agents cooperate with them. But for humans, this isn’t always the case. For example, plains indigenous groups used to leave resources for others to use at effigies called Manitokan.
1/8
I am presenting this work at the @cocomarl-workshop.bsky.social part of @rl-conference.bsky.social Tuesday (: I additionally have a generalized correction term for n-arbitrary agents (it is like walking a tree for the order of gradients) that I am looking for thoughts, validations or critiques.
Reposted by Dane Carnegie Malenfant
Super interesting. For training small LLMs, they get results comparable to those trained on an order of magnitude more tokens by replacing normal pre-training (which ingests huge amounts of human-written text) with exclusively synthetic text derived in a structured way from Wikipedia.
SYNTH is a radical departure from the classic pre-training recipe: what if we trained for reasoning and focused on the assimilation of knowledge and skill that matters? At its core it’s an upsampling of Wikipedia 50,000 “vital” articles. huggingface.co/datasets/Ple...
November 10, 2025 at 9:47 PM
Super interesting. For training small LLMs, they get results comparable to those trained on an order of magnitude more tokens by replacing normal pre-training (which ingests huge amounts of human-written text) with exclusively synthetic text derived in a structured way from Wikipedia.
I love machine learning
I love artificial intelligence
I love computer science
November 8, 2025 at 5:03 PM
I love machine learning
Reposted by Dane Carnegie Malenfant
“Our soldiers fought for the shared values of freedom and democratic rights for all. However, these soldiers returned from the war and quickly realized those freedoms and rights did not equally apply to them as they did their non-native comrades.”
#IndigenousVeteransDay
Lest We Forget
#IndigenousVeteransDay
Lest We Forget
A reflection on First Nations contributions to WW I and WW II | CBC News
Our soldiers fought for the shared values of freedom and democratic rights for all, but these soldiers returned from the war and quickly realized those freedoms and rights did not equally apply to the...
www.cbc.ca
November 8, 2025 at 4:42 PM
“Our soldiers fought for the shared values of freedom and democratic rights for all. However, these soldiers returned from the war and quickly realized those freedoms and rights did not equally apply to them as they did their non-native comrades.”
#IndigenousVeteransDay
Lest We Forget
#IndigenousVeteransDay
Lest We Forget
Reposted by Dane Carnegie Malenfant
Discover the inspiring journey of Maude Lizaire, the first Afro-descendant woman to earn a PhD at Mila, and a strong advocate for more inclusive science. mila.quebec/en/news/maud...
November 7, 2025 at 2:36 PM
Discover the inspiring journey of Maude Lizaire, the first Afro-descendant woman to earn a PhD at Mila, and a strong advocate for more inclusive science. mila.quebec/en/news/maud...
Reposted by Dane Carnegie Malenfant
A new paper with Bogdan Georgiev, Javier Gomez-Serrano, and Adam Zsolt Wagner: "Mathematical exploration and discovery at scale" arxiv.org/abs/2511.02864. Further discussion is at terrytao.wordpress.com/2025/11/05/m...
Mathematical exploration and discovery at scale
AlphaEvolve is a generic evolutionary coding agent that combines the generative capabilities of LLMs with automated evaluation in an iterative evolutionary framework that proposes, tests, and refines ...
arxiv.org
November 6, 2025 at 3:42 AM
A new paper with Bogdan Georgiev, Javier Gomez-Serrano, and Adam Zsolt Wagner: "Mathematical exploration and discovery at scale" arxiv.org/abs/2511.02864. Further discussion is at terrytao.wordpress.com/2025/11/05/m...
Reposted by Dane Carnegie Malenfant
“Edge of chaos” dynamics are long recognized as a computationally potent dynamical regime that avoids vanishing gradients during learning and allows greater memory and expressivity of a system. This stark difference surprised us, and we think it can help explain our results on neural adaptation.
November 6, 2025 at 2:10 AM
“Edge of chaos” dynamics are long recognized as a computationally potent dynamical regime that avoids vanishing gradients during learning and allows greater memory and expressivity of a system. This stark difference surprised us, and we think it can help explain our results on neural adaptation.
Reposted by Dane Carnegie Malenfant
Indeed, Lyapunov exponents show that fixed points for RL models largely stay near 0, showing these networks’ dynamics lie at the edge of chaos. Whereas SL models’ dynamics are contractive and orderly, keeping very little information in memory for long and having stereotyped expressivity.
November 6, 2025 at 2:10 AM
Indeed, Lyapunov exponents show that fixed points for RL models largely stay near 0, showing these networks’ dynamics lie at the edge of chaos. Whereas SL models’ dynamics are contractive and orderly, keeping very little information in memory for long and having stereotyped expressivity.
Reposted by Dane Carnegie Malenfant
Two Metis Nation-Saskatchewan officials were in Ottawa this week seeking funding and urgent collaborative support for culturally appropriate addictions treatment centers.
This is in response to increased addictions and gang violence seen in the area.
This is in response to increased addictions and gang violence seen in the area.
MN-S demands funding support from Ottawa for culturally appropriate treatment centers | APTN News
YouTube video by APTN News
youtu.be
November 6, 2025 at 12:48 AM
Two Metis Nation-Saskatchewan officials were in Ottawa this week seeking funding and urgent collaborative support for culturally appropriate addictions treatment centers.
This is in response to increased addictions and gang violence seen in the area.
This is in response to increased addictions and gang violence seen in the area.
1/3 Thank you to CIFAR and partners in DSET for bringing me to Banff to speak on my research: The challenge of hidden gifts in multi-agent reinforcement learning arxiv.org/abs/2505.20579. We introduce a novel task on reciprocity with a scarce resource; take what you need, leave what you don’t.
November 3, 2025 at 3:53 PM
1/3 Thank you to CIFAR and partners in DSET for bringing me to Banff to speak on my research: The challenge of hidden gifts in multi-agent reinforcement learning arxiv.org/abs/2505.20579. We introduce a novel task on reciprocity with a scarce resource; take what you need, leave what you don’t.
I’ve been finding papers that experiment with ANNs at the hardware level very interesting recently.
Such as diffusive memristors
www.nature.com/articles/s41...
Such as diffusive memristors
www.nature.com/articles/s41...
A spiking artificial neuron based on one diffusive memristor, one transistor and one resistor - Nature Electronics
An artificial neuron that is based on one diffusive memristor, one transistor and one resistor can exhibit six key biological neuronal characteristics—leaky integration, threshold firing, cascaded con...
www.nature.com
November 1, 2025 at 9:43 PM
I’ve been finding papers that experiment with ANNs at the hardware level very interesting recently.
Such as diffusive memristors
www.nature.com/articles/s41...
Such as diffusive memristors
www.nature.com/articles/s41...
Reposted by Dane Carnegie Malenfant
First Nation of Na-Cho Nyӓk Dun Elder Walter Peter never imagined he’d see himself as a hologram.
But thanks to the wonders of technology, Peter was recently turned into a nearly life-size 3D version of himself.
But thanks to the wonders of technology, Peter was recently turned into a nearly life-size 3D version of himself.
Na-Cho Nyäk Dun uses holograms to preserve culture
Elders in Mayo, Yukon are embracing hologram technology to pass down language and cultural knowledge.
www.aptnnews.ca
October 31, 2025 at 10:51 PM
First Nation of Na-Cho Nyӓk Dun Elder Walter Peter never imagined he’d see himself as a hologram.
But thanks to the wonders of technology, Peter was recently turned into a nearly life-size 3D version of himself.
But thanks to the wonders of technology, Peter was recently turned into a nearly life-size 3D version of himself.
Reposted by Dane Carnegie Malenfant
LLMs are trained to compress data by mapping sequences to high-dim representations!
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
October 31, 2025 at 4:19 PM
LLMs are trained to compress data by mapping sequences to high-dim representations!
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
I love artificial intelligence
I love computer science
October 31, 2025 at 3:27 PM
I love artificial intelligence
Reposted by Dane Carnegie Malenfant
[1/9] Excited to share our new paper "A Pragmatic View of AI Personhood" published today. We feel this topic is timely, and rapidly growing in importance as AI becomes agentic, as AI agents integrate further into the economy, and as more and more users encounter AI.
October 31, 2025 at 12:32 PM
[1/9] Excited to share our new paper "A Pragmatic View of AI Personhood" published today. We feel this topic is timely, and rapidly growing in importance as AI becomes agentic, as AI agents integrate further into the economy, and as more and more users encounter AI.
Reposted by Dane Carnegie Malenfant
[9/9] Read the full paper here:
arxiv.org/abs/2510.26396
Coauthors:
Sasha Vezhnevets,
@xtan,
@WilCunningham
arxiv.org/abs/2510.26396
Coauthors:
Sasha Vezhnevets,
@xtan,
@WilCunningham
A Pragmatic View of AI Personhood
The emergence of agentic Artificial Intelligence (AI) is set to trigger a "Cambrian explosion" of new kinds of personhood. This paper proposes a pragmatic framework for navigating this diversification...
arxiv.org
October 31, 2025 at 12:35 PM
[9/9] Read the full paper here:
arxiv.org/abs/2510.26396
Coauthors:
Sasha Vezhnevets,
@xtan,
@WilCunningham
arxiv.org/abs/2510.26396
Coauthors:
Sasha Vezhnevets,
@xtan,
@WilCunningham
Reposted by Dane Carnegie Malenfant
Writing a beautiful symphony is easier than doing the dishes in a random home
October 30, 2025 at 1:45 PM
Writing a beautiful symphony is easier than doing the dishes in a random home
Uber driver: What’s your name? Dan?
Me: yes (it’s not)
Uber driver: What a unique name
Me: yes (it’s not)
Uber driver: What a unique name
October 30, 2025 at 3:28 AM
Uber driver: What’s your name? Dan?
Me: yes (it’s not)
Uber driver: What a unique name
Me: yes (it’s not)
Uber driver: What a unique name
Reposted by Dane Carnegie Malenfant
The simplex algorithm is super efficient. 80 years of experience says it runs in linear time. Nobody can explain _why_ it is so fast.
We invented a new algorithm analysis framework to find out.
We invented a new algorithm analysis framework to find out.
Beyond Smoothed Analysis: Analyzing the Simplex Method by the Book
Narrowing the gap between theory and practice is a longstanding goal of the algorithm analysis community. To further progress our understanding of how algorithms work in practice, we propose a new alg...
arxiv.org
October 27, 2025 at 1:43 AM
The simplex algorithm is super efficient. 80 years of experience says it runs in linear time. Nobody can explain _why_ it is so fast.
We invented a new algorithm analysis framework to find out.
We invented a new algorithm analysis framework to find out.
Albania Prime Minister Edi Rama announced AI minister Diella is "pregnant" with 83 AI "children" to assist Socialist Party MPs
www.news18.com/amp/world/al...
www.news18.com/amp/world/al...
www.news18.com
October 27, 2025 at 12:42 AM
Albania Prime Minister Edi Rama announced AI minister Diella is "pregnant" with 83 AI "children" to assist Socialist Party MPs
www.news18.com/amp/world/al...
www.news18.com/amp/world/al...
Reposted by Dane Carnegie Malenfant
You don't need to be intelligent to survive! Think of viruses. Even if you think it's purely a next token predictor, when you allow the system to operate autonomously, it can survive simply by virtue of the actions it takes
AI models may be developing their own ‘survival drive’, researchers say
AI models may be developing their own ‘survival drive’, researchers say
Like 2001: A Space Odyssey’s HAL 9000, some AIs seem to resist being turned off and will even sabotage shutdown
When HAL 9000, the artificial intelligence supercomputer in Stanley Kubrick’s 2001: A Space Odyssey, works out that the astronauts onboard a mission to Jupiter are planning to shut it down, it plots to kill them in an attempt to survive.
Now, in a somewhat less deadly case (so far) of life imitating art, an AI safety research company has said that AI models may be developing their own “survival drive”. Continue reading...
www.theguardian.com
October 26, 2025 at 6:42 PM
You don't need to be intelligent to survive! Think of viruses. Even if you think it's purely a next token predictor, when you allow the system to operate autonomously, it can survive simply by virtue of the actions it takes
I love computer science
October 25, 2025 at 5:19 PM
I love computer science
Reposted by Dane Carnegie Malenfant
still true, i reckon
October 25, 2025 at 5:02 PM
still true, i reckon
Reposted by Dane Carnegie Malenfant
Paper , on social hierarchy and foraging decisions, accepted in Physical Review Research . Should be online soon on this link: doi.org/10.1103/5vfb...
October 23, 2025 at 4:37 PM
Paper , on social hierarchy and foraging decisions, accepted in Physical Review Research . Should be online soon on this link: doi.org/10.1103/5vfb...
Reposted by Dane Carnegie Malenfant
What if we did a single run and declared victory
October 23, 2025 at 2:28 AM
What if we did a single run and declared victory
Reposted by Dane Carnegie Malenfant
Haven't seen it posted a lot, so I will repost the link
medium.com/@TmlrOrg/tml...
Cool stuff, may encourage write the papers in different tempo
medium.com/@TmlrOrg/tml...
Cool stuff, may encourage write the papers in different tempo
TMLR joins NeurIPS/ICML/ICLR Journal-to-Conference Track
Great news! We’re excited to announce that selected papers published in the Transactions on Machine Learning Research (TMLR) will now be…
medium.com
October 22, 2025 at 8:53 PM
Haven't seen it posted a lot, so I will repost the link
medium.com/@TmlrOrg/tml...
Cool stuff, may encourage write the papers in different tempo
medium.com/@TmlrOrg/tml...
Cool stuff, may encourage write the papers in different tempo