Dane Carnegie Malenfant
MSc. @mila-quebec.bsky.social and @mcgill.ca in the LiNC lab
Fixating on multi-agent RL, Neuro-AI and decisions
Ēka ē-akimiht
danemalenfant.com
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie MalenfantHi, Indigenous person here. I've never seen any of the avatar movies, and after what James Cameron said about the Lakota people, I never will.
- Reposted by Dane Carnegie MalenfantCanada lynx
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie MalenfantThe Abenaki council of Odanak and Wôlinak in Quebec launches an advertising campaign in the state of Vermont in the United States to raise awareness about the misrepresentation of Abenaki identity in their state.
- Reposted by Dane Carnegie MalenfantTwo agreements with the uranium mining company Denison Mines has been signed with Metis Nation-Saskatchewan. The agreements ensure Metis voices are included in mining decisions in northern Saskatchewan.
- Reposted by Dane Carnegie MalenfantMcGill’s Celeste Pedri-Spade: “[‘Pretendians’] become a kind of counterfeit currency, granting Canadians easy access to digestible versions of Indigenous identity and experience. But they are not ours, they are not us and they are not our stories” theconversation.com/thomas-king-...
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie MalenfantWatercolor portrait of Joe Healy, "the most educated Indian on the reserve," was painted by Nora Foote, a British artist who visited what is now Saskatchewan and Alberta in 1895. As a boy, Healy was a witness to the Marias Massacre in Montana,
- Reposted by Dane Carnegie MalenfantAn Ontario Superior Court judge has dismissed a lawsuit that accuses the current president of the Manitoba Métis Federation and a former president of the Métis National Council (MNC) of misappropriating millions of dollars of the MNC’s funds.
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie Malenfant(everyone has known for years — years!! — that Thomas King is not Cherokee) www.theglobeandmail.com/culture/book...
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- I love machine learning
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie MalenfantDiscover 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 MalenfantA 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.
- Reposted by Dane Carnegie MalenfantIndeed, 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[Not loaded yet]
- 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.
- 2/3 It was wonderful to see machine learning’s impact across so many fields. Especially work from Taiwan. Like Canada, Taiwan has Indigenous peoples; I believe cultural and traditional knowledge can strengthen ML systems and how they generalize and align to real-world contexts.
- 3/3 Also appreciating the aura farming from seeing my photo in Taiwanese newspapers haha. Grateful to the organizers and everyone who joined the discussion! www.ctee.com.tw/news/2025102...
- 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...
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie MalenfantLLMs 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
- 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.
-
View full threadReposted by Dane Carnegie Malenfant[9/9] Read the full paper here: arxiv.org/abs/2510.26396 Coauthors: Sasha Vezhnevets, @xtan, @WilCunningham
- Reposted by Dane Carnegie MalenfantWriting 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
- Reposted by Dane Carnegie MalenfantThe 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.
- 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...
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- I love computer science
- Reposted by Dane Carnegie Malenfantstill true, i reckon
- Reposted by Dane Carnegie MalenfantPaper , 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 MalenfantWhat if we did a single run and declared victory
- Reposted by Dane Carnegie MalenfantHaven'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
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- I really enjoy reading equations in formal fields (e.g math, computer science, et.c) due to all the colours and shapes that appear in your mind but making low math public outreach posters is fun too @ivado.bsky.social @mila-quebec.bsky.social
- A nice feeling after long long hours
- 5 pages longer than @veds12.bsky.social ‘s
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie Malenfant🚀 Excited to share a major update to our “Mixture of Cognitive Reasoners” (MiCRo) paper! We ask: What benefits can we unlock by designing language models whose inner structure mirrors the brain’s functional specialization? More below 🧠👇 cognitive-reasoners.epfl.ch
- To follow up on the asymptotic proof that the self-correction term works with any number of agents or coalitions, here are the results for 3 agents. Policy gradient agent's performance suffers with more agents but self correction still stabilizes learning arxiv.org/abs/2505.20579
- Scaling the self-correction term is functionally as the more agents that contribute to a reward increase the gradient order for inferring how those agents effect your Q-value estimate of your collective sub-policy. All still computed in O(N) time where N is the number of agents.
- The challenge of hidden gifts is more difficult with more agents but still solvable
- Reposted by Dane Carnegie MalenfantIn 2018, Charles Murray challenged me to a bet: "We will understand IQ genetically—I think most of the picture will have been filled in by 2025—there will still be blanks—but we’ll know basically what’s going on." It's now 2025, and I claim a win. I write about it in The Atlantic.
- So that’s what model welfare is for
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Reposted by Dane Carnegie MalenfantI am seeing a lot of people reposting Lakota Man today bc it's Indigenous Peoples Day. A reminder that he is not well liked amongst many (most?) Natives on social media. Many of us blocked him a long time ago. Some of the reasons why are in this article. www.dailydot.com/irl/lakotama...
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- Here is my plan to make Bluesky more fun and active:
- Reposted by Dane Carnegie Malenfant[Not loaded yet]
- 1/8 A month ago I wrapped a 4-month project with MuTek Forum’s AI Ecologies Lab led by Sarah Mackenzie: the research arm of Montréal’s 25-year electronic music festival. Why entropy can make AI more resilient Event: ra.co/events/2206981
- 2/8 I proposed a reinforcement-learning (RL) demo: add a maximum-entropy term to increase the longevity of systems in a non-stationary environment. This is well known to the RL research community: openreview.net/forum?id=PtS... (photo by Félix Bonne-Vie)
- 3/8 By training systems this way, agents should handle non-stationary changes better. Yet outside research circles, “AI” ≈ only LLMs or generative models. RL, on the other hand, is an unknown learning paradigm to the public’s eyes.
-
View full thread8/8 Further context in this recap captures the AI Ecologies Lab: hacnumedia.org/creer-avec-l..., raav.org/actuality/qu... and lienmultimedia.com/spip.php?art... . The festival is mutek.org
- My eye colour apparently changed after 6 years
- Reposted by Dane Carnegie MalenfantWe're finally out of stealth: percepta.ai We're a research / engineering team working together in industries like health and logistics to ship ML tools that drastically improve productivity. If you're interested in ML and RL work that matters, come join us 😀
- I am on one transformer paper from 3 years ago and ICLR flooded my bids with RLVR & RLHF :S
- Reposted by Dane Carnegie Malenfantw/ James Cohan, @jacobeisenstein.bsky.social, and Kristina Toutanova Paper link: arxiv.org/abs/2509.22445
