LLMs can do math or plan a schedule. But can they do the math and then plan the schedule, without falling apart?
This week, U of T PhD student Yongjin Yang joins us to introduce Skill Entropy: measuring models performance when forced to juggle different skills.
We’re back at Trinity Bellwoods Park this Saturday☀️📚
Diving into papers on linear attention - including Gated Delta Nets and Sparse Delta Memory.
Whether you're deeply into the math or just curious about the latest in AI, you’re welcome to join the convo!
Sign up below
The J-space lets us read, audit, and shape what Claude is actively thinking about—useful tools for keeping models trustworthy as they grow more capable. And it suggests surprising parallels between language models and our own minds.
Read the full paper: https://t.co/ge3uqY59DU
As always, if you are in Toronto, interested in discussing/learning about ML, come join us! We are at Trinity Bellwoods every Saturday at noon. https://t.co/k7ccctYx0B
We are halfway through S2 for Papers in the Park!
There's been rain. There's been heatwaves. We've been joined by squirrels and sparrows hungry for knowledge. I found a spot to see the CN Tower from, so I can finally replace the stock photos we've been using since S1
Feeling happy free confused in the best way because we just did our 22nd event last week!
Come join us again SUNDAY (not Saturday this time) for a discussion around DSpark and the Meta Brain2Qwerty paper, and hopefully celebrating more than just ML advances by then 🇨🇦⚽🇨🇦⚽
Week 17 of Papers in the P̶a̶r̶k̶ 🌧️
Thanks everyone for coming through despite the downpour, and especially to DiFan for his insightful presentation about his new paper!
Shout out to our Open Science Leads @asusevski
and @alvanlii for leading 14 paper reading sessions! Each week they gathered in the park with pizza + papers and dove into the research with their group. 🍕 🏞️
An album of highlight from the summer in TO to inspire joy wherever you are. 😊