'A nice day to wash clothes' | Allen Sapp (Cree) 1928-2015 Private Collection

Excited to share that POSSM has been accepted to #NeurIPS2025! See you in San Diego 🏖️

I had a lot of fun attending and presenting the Challenge of Hidden Gifts at @ewrl18.bsky.social ! openreview.net/forum?id=gbs... Tübingen is a great city and it was nice to get out of the North American machine learning bubble.

The cerebellum isn’t just about coordinating movement. It’s implicated in nearly every domain of cognition—from language to social behavior. But how exactly does the cerebellum contribute to action and cognition? 🧵 Check out our new paper w/ Rich Ivry. arxiv.org/abs/2509.09818

Why do LLMs fail at long horizon tasks? Because errors in execution, not planning i.e. an error made early on conditions the LLM into a bad state later. Newer agentic LLMs deal with early errors better arxiv.org/abs/2509.09677

Both leaders and followers integrate partner position into their decision-making, exerting asymmetric yet reciprocal influence. Forward multi-agent RL (MARL) shows simulated agents can learn the task and also develop stable leader–follower dynamics, suggesting social roles can self-organize (2/5)

Super excited to share the first cooperative foraging paradigm in freely interacting mouse pairs! Stable leader and follower roles emerge spontaneously and predict learning. Well-trained mice show stereotyped, role-specific “behavioral motifs” absent in naive animals (1/5) doi.org/10.1101/2025...

𝗪𝗵𝗲𝗿𝗲 𝗱𝗼 𝗿𝗲𝘄𝗮𝗿𝗱𝘀 (𝘃𝗮𝗹𝘂𝗲) 𝗰𝗼𝗺𝗲 𝗳𝗿𝗼𝗺? Implications for reinforcement learning. Very interesting paper. doi.org/10.1016/j.ti... #neuroskyence

phrase, “Graham Greene, Native actor.” You don’t hear people say, “Denzel Washington, black actor,” or “Kevin Costner, white actor.” Photo: Defiance | Universal/Trion Worlds

Graham Greene also pushed against typecasting and believed that Native actors could play any role; that we don't have to be segregated, or limited, to the "Indigenous section." This interview with Readers Digest: You recently appeared in Te Ata, a…

'You know some girls are bright as the morning And some girls are blessed with a dark turn of mind' music.youtube.com/watch?v=57ms...

Vision-Language-Action models are the foundation of a new wave of generalist robots: networks that take in images from robot cameras (vision) and instructions (language) and produce robot trajectories. We are seeing a remarkable convergence in how these work; more: open.substack.com/pub/itcanthi...

Global cooperation & coordination are among the most urgent tasks to mitigate AI risks & ensure the technology benefits all. Congratulations to the United Nations on establishing the Independent International Scientific Panel on AI & the Global Dialogue on AI Governance. media.un.org/unifeed/en/a...

Proud of Amy and Nick, who review technical and theoretical gaps in timescales of dopamine fluctuations. We argue that DA fluctuations are hierarchical control signals, and “tonic” DA relays goal alignment across planning horizons and C-BG hierarchy. www.sciencedirect.com/science/arti...

Ok small rant: I don't think we're in a generative AI bubble. Actual market is still small. It seems bigger only because all kinds of things (and liabilities) are labelled "AI" now. Long overdue infrastructure update? For AI. Having to cut jobs? Because of AI. Fundraising? Quick add AI to name.

The Métis Nation - Saskatchewan have declared a state-of-emergency to address a drug and alcohol-fueled crisis of gang violence in its communities. Leaders warn that more lives will be lost and families will be affected if something isn't done.

New talk by Dr. Peter Dayan, theoretical neuroscientist and one of the leading experts on reinforcement learning in brains and machines. #neuroAI #compneuro #AI #neuroscience www.youtube.com/watch?v=2OOG...

Excited for everyone to stop watching TV since it's less energy efficient than using Gemini. Morally you simply must

ฅ^•ﻌ•^ฅ

The “proof” to the below thread in one page

Very excited to release a new blog post that formalizes what it means for data to be compositional, and shows how compositionality can exist at multiple scales. Early days, but I think there may be significant implications for AI. Check it out! ericelmoznino.github.io/blog/2025/08...

This project was 4 years in the making and it's finally out! We found that controlling vehicle speeds to mitigate traffic across a city can cut carbon emissions between 11 and 22 percent. To do this, we used deep reinforcement learning to optimize one million eco-driving scenarios. 🚗🤖🧠

People assume wrongly that it's like a support vector machine where the math that does the inference is fairly tractable and we know the rough algorithm it learns to accomplish the task. No, we actually do not know here it's too abstract and opaque.

Breaking: the team investigating the Kuper Island Residential School in BC has confirmed 171 children deaths at the institution, 50 more than previously known. As a residential school historian and someone fighting residential school denialism, here's a 🧵 www.timescolonist.com/local-news/a...

if you didn't catch Juliana Trach's poster at @cogscisociety.bsky.social here it is ––>

HRM analysis by @dorialexander.bsky.social the actual shocking parts: * it doesn’t overfit * ARC-AGI is only hard for language models i think we’ll be seeing more of HRM

Is the Language of Thought == Language? A Thread 🧵 New Preprint (link: tinyurl.com/LangLOT) with @alexanderfung.bsky.social, Paris Jaggers, Jason Chen, Josh Rule, Yael Benn, @joshtenenbaum.bsky.social, ‪@spiantado.bsky.social‬, Rosemary Varley, @evfedorenko.bsky.social 1/8

"AI researchers slowly but surely work their way towards the mid-2000s in psych research" is genuinely funny as a convergence situation

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.

it uses a Self-supervised Process Reward Model (SPRM) to grade several reasoning trajectories the SPRM is a different model, but mostly not. Same base + 53M for the grading

A recent poll found just 38 per cent of non-Indigenous people in Saskatchewan trust Indigenous Peoples, far below the national average. On the latest Truth and Politics, Jennifer Laewetz shares her perspective on why that gap exists. Full discussion: pod.fo/e/307e4b

Watercolor 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, when over 200 Blackfeet women, children and elders were

HRM: Hierarchical Reasoning Model ngl this sounds like bullshit but i don’t think it is - 27M (million parameters) - 1000 training examples - beats o3-mini on ARC-AGI arxiv.org/abs/2506.21734

We had a storm roll through last night in the forest and I was thinking about how I prefer to being able to see them coming like on the prairies. However, once they are on top of you, it’s a whole lot more scary because there is nowhere to hide. This was taken a week ago in Grasslands National Park.

After being in Montréal for 7 years, I’ve always really appreciated being able to walk at night. I think my dad’s home city (below) and my birth city (North Battleford) are the only Canadian cities with adult crime curfews. Maybe also somewhere in Manitoba or Alberta?

Trying to train RNNs in a biol plausible (local) way? Well, try our new method using predictive alignment. Paper just out in Nat. Com. Toshitake Asabuki deserves all the credit! www.nature.com/articles/s41...

Visiting my cat 😺

In 2023 I reported on the impacts of wildfires in northern Saskatchewan, which not only endanger human life and communities but also cultural and ecological resources. It's heartbreaking to be covering it again, as Canada experiences another brutal year for wildfires.

Southern Saskatchewan has many off the road gems. Castle Butte is one of them. This massive sandstone/clay formation was created along with the rest of the Big Muddy Badlands when a giant glacial lake experienced a catastrophic drainage, carving a massive butte-filled valley. 1/2

🧵 Everyone is chasing new diffusion models—but what about the representations they model from? We introduce Discrete Latent Codes (DLCs): - Discrete representation for diffusion models - Uncond. gen. SOTA FID (1.59 on ImageNet) - Compositional generation - Integrates with LLM 🧱

These are systems that respond to human writing and (often) techniques that apply to human psychology. The Math Olympiad is great, coding is important, accelerating science has tremendous value. But LLMs give a chance for both cultures to contribute in ways that have not been possible for a while.

Hi, are you a journalist or know a journalist who likes to point out that LLMs are “stochastic parrots”? Happy to offer my services explaining why this is not accurate

The Woodland Cree First Nation in Alberta is getting into the world of A.I. by starting work on a six hundred and fifty-gigawatt datacentre. Their chief, Isaac Laboucan-Avirom, says it can provide good jobs and be environmentally friendly.

1970 presentation in Ottawa of The "Red Paper,” an official Indian response to the 1969 "White Paper" of the Liberal government. Walter Deiter, headdress, presenting to PM Pierre Trudeau and Indian Affairs Minister Jean Chretien. 📷 Duncan Cameron | Library and Archives Canada

I really like how @weightsbiases.bsky.social plots the KL with multi-agent PPO

That’s a wrap on the Indigenous AI Gathering 2025. Over two days, Indigenous knowledge keepers, technologists, youth, and allies came together to chart new paths in AI inclusive of Indigenous ethics and perspectives. Thank you for being part of this vital conversation.

Congratulations to Matthew Sanspareil and Rune Hartgerink, the winning team of the Indigenous Pathfinders in AI program’s pitch day! Their project, Buffalo in Motion, uses AI to strengthen food sovereignty through buffalo restoration.

As Elder Deborah Delisle opened with the Ohén:ton Karihwatéhkwen and drumming filled the space, the Indigenous AI Gathering got underway this morning — a powerful start to this celebration of Indigenous-led AI innovation. With Abundant Intelligences, @indspire.bsky.social and @ivado.bsky.social.