Danica Sutherland
@djsutherland.ml
machine learning asst prof at @cs.ubc.ca and amii
statistical testing, kernels, learning theory, graphs, active learning…
she/her, 🏳️⚧️, @queerinai.com
statistical testing, kernels, learning theory, graphs, active learning…
she/her, 🏳️⚧️, @queerinai.com
Come join us in a great department in a great city! I'm not on the search committee, but feel free to be in touch if you have any questions or anything.
UBC Computer Science invites applications for up to two full-time tenure-track positions with the following priority areas: visualization, robotics, reinforcement learning, data management, and data mining. Applications are due Wed Dec 10, 2025. Learn more: www.cs.ubc.ca/our-departme...
October 27, 2025 at 7:38 PM
Come join us in a great department in a great city! I'm not on the search committee, but feel free to be in touch if you have any questions or anything.
Reposted by Danica Sutherland
REMINDER!! We hope to see you all ✨TODAY✨ for our social! Check out queerinai.com/icml-2025 for further details! 🌈🌈
July 16, 2025 at 9:47 PM
REMINDER!! We hope to see you all ✨TODAY✨ for our social! Check out queerinai.com/icml-2025 for further details! 🌈🌈
Reposted by Danica Sutherland
1/ 💻 Queer in AI is hosting a social at #ICML2025 in Vancouver on 📅 July 16, and you’re invited! Let’s network, enjoy food and drinks, and celebrate our community. Details below…
July 4, 2025 at 4:08 PM
1/ 💻 Queer in AI is hosting a social at #ICML2025 in Vancouver on 📅 July 16, and you’re invited! Let’s network, enjoy food and drinks, and celebrate our community. Details below…
As things get ever worse in the UK and the US releases sloppy political “reviews” of bad science (magnified by the NYT/Atlantic/etc), a good reminder for anyone who has “concerns” about trans youth care.
(Canada seems okay federally for now, but AB/SK are going in v bad directions.)
(Canada seems okay federally for now, but AB/SK are going in v bad directions.)
New on the blog, something I've been meaning to write for a long time. As we get ready for HHS to ramp up its attacks on our care, let's take a minute to remember why it matters: because we do, and we deserve lives worthy of living.
In defense of trans quality of life — Jessica Kant
Today trans people exist in an atmosphere where it has become normal for strangers to demand of us that we extemporaneously provide inarguable, indisputable proof that without very safe medical care w...
jessk.org
May 1, 2025 at 3:23 PM
As things get ever worse in the UK and the US releases sloppy political “reviews” of bad science (magnified by the NYT/Atlantic/etc), a good reminder for anyone who has “concerns” about trans youth care.
(Canada seems okay federally for now, but AB/SK are going in v bad directions.)
(Canada seems okay federally for now, but AB/SK are going in v bad directions.)
AI Scientist making the funniest possible citation mistake (Goodfellow instead of Schmidhuber)
April 28, 2025 at 7:00 AM
AI Scientist making the funniest possible citation mistake (Goodfellow instead of Schmidhuber)
Reposted by Danica Sutherland
Join us tomorrow for our official social at #ICLR2025 on Saturday, 04/26, 5:00 - 6:30 pm in the GHJ room ("hidden" between Hall 2 and 3)! We can’t wait to see you all and to mingle! After the social ends, we will also set out for an unofficial bar tour of downtown Singapore.
Queer in AI @ ICLR 2025: Social Sign-In Survey
Please note that most fields below are optional. We also strongly encourage you to fill out the Queer in AI Demographics Survey which provides QinAI with information about our community we use to help...
forms.gle
April 25, 2025 at 9:30 AM
Join us tomorrow for our official social at #ICLR2025 on Saturday, 04/26, 5:00 - 6:30 pm in the GHJ room ("hidden" between Hall 2 and 3)! We can’t wait to see you all and to mingle! After the social ends, we will also set out for an unofficial bar tour of downtown Singapore.
Thrilled to announce that Joshua’s paper won one of three Outstanding Paper awards at ICLR.
Come to the poster on Friday afternoon (#376 in Hall 3) or the talk on Saturday (4:30 in Hall 1), and while you’re at it snag him for a postdoc!
Come to the poster on Friday afternoon (#376 in Hall 3) or the talk on Saturday (4:30 in Hall 1), and while you’re at it snag him for a postdoc!
📢Curious why your LLM behaves strangely after long SFT or DPO?
We offer a fresh perspective—consider doing a "force analysis" on your model’s behavior.
Check out our #ICLR2025 Oral paper:
Learning Dynamics of LLM Finetuning!
(0/12)
We offer a fresh perspective—consider doing a "force analysis" on your model’s behavior.
Check out our #ICLR2025 Oral paper:
Learning Dynamics of LLM Finetuning!
(0/12)
April 23, 2025 at 7:54 AM
Thrilled to announce that Joshua’s paper won one of three Outstanding Paper awards at ICLR.
Come to the poster on Friday afternoon (#376 in Hall 3) or the talk on Saturday (4:30 in Hall 1), and while you’re at it snag him for a postdoc!
Come to the poster on Friday afternoon (#376 in Hall 3) or the talk on Saturday (4:30 in Hall 1), and while you’re at it snag him for a postdoc!
Reposted by Danica Sutherland
📢Curious why your LLM behaves strangely after long SFT or DPO?
We offer a fresh perspective—consider doing a "force analysis" on your model’s behavior.
Check out our #ICLR2025 Oral paper:
Learning Dynamics of LLM Finetuning!
(0/12)
We offer a fresh perspective—consider doing a "force analysis" on your model’s behavior.
Check out our #ICLR2025 Oral paper:
Learning Dynamics of LLM Finetuning!
(0/12)
April 21, 2025 at 5:45 AM
📢Curious why your LLM behaves strangely after long SFT or DPO?
We offer a fresh perspective—consider doing a "force analysis" on your model’s behavior.
Check out our #ICLR2025 Oral paper:
Learning Dynamics of LLM Finetuning!
(0/12)
We offer a fresh perspective—consider doing a "force analysis" on your model’s behavior.
Check out our #ICLR2025 Oral paper:
Learning Dynamics of LLM Finetuning!
(0/12)
From the intro to a paper I'm reading:
"Theorem 3 is proven in Section 4 and Theorem 4 is proven in Section 3."
😔
"Theorem 3 is proven in Section 4 and Theorem 4 is proven in Section 3."
😔
February 13, 2025 at 7:22 AM
From the intro to a paper I'm reading:
"Theorem 3 is proven in Section 4 and Theorem 4 is proven in Section 3."
😔
"Theorem 3 is proven in Section 4 and Theorem 4 is proven in Section 3."
😔
What happens when models, like LLMs, learn from each other across multiple generations?
@joshuaren.bsky.social + collaborators extend a cogsci framework called Bayesian iterated learning to think about, and avoid, pitfalls.
#NeurIPS2024 poster #3305, Friday 11-2
(Also, snag him for a postdoc 😇)
@joshuaren.bsky.social + collaborators extend a cogsci framework called Bayesian iterated learning to think about, and avoid, pitfalls.
#NeurIPS2024 poster #3305, Friday 11-2
(Also, snag him for a postdoc 😇)
December 13, 2024 at 9:55 AM
What happens when models, like LLMs, learn from each other across multiple generations?
@joshuaren.bsky.social + collaborators extend a cogsci framework called Bayesian iterated learning to think about, and avoid, pitfalls.
#NeurIPS2024 poster #3305, Friday 11-2
(Also, snag him for a postdoc 😇)
@joshuaren.bsky.social + collaborators extend a cogsci framework called Bayesian iterated learning to think about, and avoid, pitfalls.
#NeurIPS2024 poster #3305, Friday 11-2
(Also, snag him for a postdoc 😇)
This analysis of how attention scores work in graph transformers was pretty surprising to me, and enabled the rest of this paper (and hopefully more!). Come check out the poster soon!
As a reminder, we will have our poster session tomorrow:
📍 East Exhibit Hall, Poster #3010
📄 arxiv.org/abs/2411.16278
💻 github.com/hamed1375/Sp...
To motivate you further, we have some insights gained from the attention score analysis of this work, which I'll share in this thread:
📍 East Exhibit Hall, Poster #3010
📄 arxiv.org/abs/2411.16278
💻 github.com/hamed1375/Sp...
To motivate you further, we have some insights gained from the attention score analysis of this work, which I'll share in this thread:
Graph Transformers (GTs) can handle long-range dependencies and resolve information bottlenecks, but they’re computationally expensive. Our new model, Spexphormer, helps scale them to much larger graphs – check it out at NeurIPS next week, or the preview here!
[1/13]
#NeurIPS2024
[1/13]
#NeurIPS2024
December 12, 2024 at 6:21 PM
This analysis of how attention scores work in graph transformers was pretty surprising to me, and enabled the rest of this paper (and hopefully more!). Come check out the poster soon!
Reposted by Danica Sutherland
As in Tennessee, this ban does not apply to cis children, because the drugs themselves are not a safety hazard. The only thing at risk is a society’s discomfort with allowing young people to make their own decisions about their own bodies.
Puberty blockers to be banned indefinitely for under-18s across UK
Puberty blockers to be banned indefinitely for under-18s across UK
Health secretary says emergency measures banning sale and supply will be made indefinite after expert advice
Puberty blockers for under-18s with gender dysphoria will be banned indefinitely across the UK, except for use in clinical trials, the government…
www.theguardian.com
December 11, 2024 at 2:49 PM
As in Tennessee, this ban does not apply to cis children, because the drugs themselves are not a safety hazard. The only thing at risk is a society’s discomfort with allowing young people to make their own decisions about their own bodies.
Reposted by Danica Sutherland
Graph Transformers (GTs) can handle long-range dependencies and resolve information bottlenecks, but they’re computationally expensive. Our new model, Spexphormer, helps scale them to much larger graphs – check it out at NeurIPS next week, or the preview here!
[1/13]
#NeurIPS2024
[1/13]
#NeurIPS2024
December 5, 2024 at 7:58 PM
Graph Transformers (GTs) can handle long-range dependencies and resolve information bottlenecks, but they’re computationally expensive. Our new model, Spexphormer, helps scale them to much larger graphs – check it out at NeurIPS next week, or the preview here!
[1/13]
#NeurIPS2024
[1/13]
#NeurIPS2024
Reposted by Danica Sutherland
🌈🌈We have an incredible day planned for you at our #QueerInAI workshop at #NeurIPS2024 in Vancouver on December 11! You can join us in person or virtually via live-stream! Find out more about our events and our lovely speakers at queerinai.com/neurips-2024!! ✨✨
December 3, 2024 at 9:50 PM
🌈🌈We have an incredible day planned for you at our #QueerInAI workshop at #NeurIPS2024 in Vancouver on December 11! You can join us in person or virtually via live-stream! Find out more about our events and our lovely speakers at queerinai.com/neurips-2024!! ✨✨
Well, I don’t know what else I was expecting.
November 22, 2024 at 7:39 AM
Well, I don’t know what else I was expecting.
Reposted by Danica Sutherland
Periodic reminder: submitting on #arXiv is great! But the source is available: good per se, but remember to remove LaTeX comments you don't want to be made public.
Thankfully, there are tools that do that (and more) easily and automatically for you! E.g., arXiv-collector:
github.com/djsutherland...
Thankfully, there are tools that do that (and more) easily and automatically for you! E.g., arXiv-collector:
github.com/djsutherland...
GitHub - djsutherland/arxiv-collector: A little Python script to collect LaTeX sources for upload to the arXiv.
A little Python script to collect LaTeX sources for upload to the arXiv. - djsutherland/arxiv-collector
github.com
November 18, 2024 at 2:35 AM
Periodic reminder: submitting on #arXiv is great! But the source is available: good per se, but remember to remove LaTeX comments you don't want to be made public.
Thankfully, there are tools that do that (and more) easily and automatically for you! E.g., arXiv-collector:
github.com/djsutherland...
Thankfully, there are tools that do that (and more) easily and automatically for you! E.g., arXiv-collector:
github.com/djsutherland...