https://www.aicentre.dk/
Project page: sjyhne.github.io/superf/
Preprint: www.arxiv.org/abs/2512.09115
Demo: huggingface.co/spaces/sjyhn...
Thread [1/n] 👇
Thanks to the Pioneer Centre for AI (@aicentre.dk) and the Global Wetland Center for supporting this project. [n/n]
Thanks to the Pioneer Centre for AI (@aicentre.dk) and the Global Wetland Center for supporting this project. [n/n]
We're kicking off the series with @serge.belongie.com, ELLIS Board Pres, Director at @aicentre.dk & Prof at the Uni Copenhagen 🇩🇰.
He tackles rapid-fire AI questions—from AGI to algorithms—& recommends this paper: peterfmichael.com/nci
Watch now 👉 youtu.be/Hj9A59EPGzM
We're kicking off the series with @serge.belongie.com, ELLIS Board Pres, Director at @aicentre.dk & Prof at the Uni Copenhagen 🇩🇰.
He tackles rapid-fire AI questions—from AGI to algorithms—& recommends this paper: peterfmichael.com/nci
Watch now 👉 youtu.be/Hj9A59EPGzM
Find more about each of them below 🧵👇
#NLP #NLProc #EMNLP2025 @itu.dk @aicentre.dk
Find more about each of them below 🧵👇
#NLP #NLProc #EMNLP2025 @itu.dk @aicentre.dk
Exited to share our latest work where we answer this question positively.
Spiking Patches: Asynchronous, Sparse, and Efficient Tokens for Event Cameras
Paper: arxiv.org/abs/2510.26614
Minimizing False-Positive Attributions in Explanations of Non-Linear Models
#NeurIPS2025
Thanks to my supervisor @lars-kai-hansen.bsky.social and to @sparsity.bsky.social. Supported by @novo-nordisk.bsky.social , @aicentre.dk , and DDSA.
Paper: arxiv.org/abs/2505.11210
Minimizing False-Positive Attributions in Explanations of Non-Linear Models
#NeurIPS2025
📢 Call for Participation: sites.google.com/g.harvard.ed...
Confirmed speakers from Mistral AI, DeepMind, ETH Zurich, LSCE & more.
Looking forward to meeting and discussing in Copenhagen!
EurIPS takes place over 3 days + 2 workshop days, at the same time as NeurIPS in San Diego.
Follow this account for more updates, and see you in wonderful Copenhagen 📅
eurips.cc
EurIPS takes place over 3 days + 2 workshop days, at the same time as NeurIPS in San Diego.
Follow this account for more updates, and see you in wonderful Copenhagen 📅
eurips.cc
@ulrikeluxburg.bsky.social
Michael Jordan
Emtiyaz Khan
Amnon Shashua
More details to come as we get closer to December, so stay tuned
@ulrikeluxburg.bsky.social
Michael Jordan
Emtiyaz Khan
Amnon Shashua
More details to come as we get closer to December, so stay tuned
"Unstructured Evidence Attribution for Long Context Query Focused Summarization"
w/ @zainmujahid.me , Lu Wang, @iaugenstein.bsky.social , and @davidjurgens.bsky.social
"Unstructured Evidence Attribution for Long Context Query Focused Summarization"
w/ @zainmujahid.me , Lu Wang, @iaugenstein.bsky.social , and @davidjurgens.bsky.social
borsen.dk/nyheder/pers...
borsen.dk/nyheder/pers...
www.sciencedirect.com/science/arti...
www.sciencedirect.com/science/arti...
🔗Find information on Program, Talks, Speakers and Registration here: www.aicentre.dk/events/works...
🔗Find information on Program, Talks, Speakers and Registration here: www.aicentre.dk/events/works...
Peter Michael, Zekun Hao, @serge.belongie.com , and Abe Davis, “Noise-Coded Illumination for Forensic and Photometric Video Analysis,” ACM Transactions on Graphics, 2025.
Peter Michael, Zekun Hao, @serge.belongie.com , and Abe Davis, “Noise-Coded Illumination for Forensic and Photometric Video Analysis,” ACM Transactions on Graphics, 2025.
We look forward to making #EurIPS a diverse and inclusive event with you.
The submission deadlines are August 22nd, AoE.
More information at:
eurips.cc/call-for-wor...
eurips.cc/call-for-aff...
We look forward to making #EurIPS a diverse and inclusive event with you.
The submission deadlines are August 22nd, AoE.
More information at:
eurips.cc/call-for-wor...
eurips.cc/call-for-aff...
We had 7 inspiring keynotes, 26 poster presentations, and there was time for informal mingling as well.
Thanks to DSSA for the generous support.
See some of you in Vienna for #acl2025nlp! #NLProc
aicentre.dk/events/pre-acl
Check out the explainer: ai-research.andersgiovanni.com
Check out the explainer: ai-research.andersgiovanni.com
Find more about each of them below 🧵👇
#NLP #NLProc #ACL2025NLP @itu.dk @aicentre.dk
Find more about each of them below 🧵👇
#NLP #NLProc #ACL2025NLP @itu.dk @aicentre.dk
PALM enables theory-driven evaluation and forecasting of AL performance in budget-constrained settings.
Julia Machnio
@mostafaghazi.bsky.social
Mads Nielsen
PALM enables theory-driven evaluation and forecasting of AL performance in budget-constrained settings.
Julia Machnio
@mostafaghazi.bsky.social
Mads Nielsen
arxiv.org/abs/2506.19552
arxiv.org/abs/2506.19552
Main points:
1. Hubness is not a problem when language models do next-token prediction.
2. Nuisance hubness can appear when other comparisons are made.
www.nature.com/articles/s41...
Great work,
@lenkatetkova.bsky.social and team!
www.nature.com/articles/s41...
Great work,
@lenkatetkova.bsky.social and team!
www.aicentre.dk/phd-openings
www.aicentre.dk/phd-openings
🗒️ Add your expression of interest to join @copenlu.bsky.social here by 20 July: forms.office.com/e/HZSmgR9nXB
Selected candidates will be invited to submit a DARA fellowship application with me: daracademy.dk/fellowship/f...
🗒️ Add your expression of interest to join @copenlu.bsky.social here by 20 July: forms.office.com/e/HZSmgR9nXB
Selected candidates will be invited to submit a DARA fellowship application with me: daracademy.dk/fellowship/f...