okay i need urgent help for a talk i am delivering tomorrow:
suppose you classify all the unireps of Poincare a la Wigner. how would you explain to a non-physicist audience why you identify the parameter m as mass?
suppose you classify all the unireps of Poincare a la Wigner. how would you explain to a non-physicist audience why you identify the parameter m as mass?
November 11, 2025 at 5:29 PM
okay i need urgent help for a talk i am delivering tomorrow:
suppose you classify all the unireps of Poincare a la Wigner. how would you explain to a non-physicist audience why you identify the parameter m as mass?
suppose you classify all the unireps of Poincare a la Wigner. how would you explain to a non-physicist audience why you identify the parameter m as mass?
🎥 The recording of the last ELLIS x UniReps session with
@stefanofusi.bsky.social & @danielkunin.bsky.social is now available on YouTube! Watch here: youtu.be/t5FTQ3tthBA
@stefanofusi.bsky.social & @danielkunin.bsky.social is now available on YouTube! Watch here: youtu.be/t5FTQ3tthBA
ELLISxUniReps Seventh Session (October 28th) - with S. Fusi and D. Kunin
YouTube video by Unifying Representations in Neural Models
youtu.be
October 30, 2025 at 12:01 PM
🎥 The recording of the last ELLIS x UniReps session with
@stefanofusi.bsky.social & @danielkunin.bsky.social is now available on YouTube! Watch here: youtu.be/t5FTQ3tthBA
@stefanofusi.bsky.social & @danielkunin.bsky.social is now available on YouTube! Watch here: youtu.be/t5FTQ3tthBA
Join the upcoming ELLIS x UniReps @unireps.bsky.social Speaker Session Session in October focusing on DINOv3 and its representation alignment with the human brain!
📅 Oct 8
🕓 16:00-17:00 CET
📍 Virtual
🔗 https://ellis.eu/events/ellis-reading-group-ellisxunireps-speaker-series-session
📅 Oct 8
🕓 16:00-17:00 CET
📍 Virtual
🔗 https://ellis.eu/events/ellis-reading-group-ellisxunireps-speaker-series-session
ELLIS Reading Group: ELLISxUniReps Speaker Series Session
The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...
ellis.eu
September 30, 2025 at 11:29 AM
Join the upcoming ELLIS x UniReps @unireps.bsky.social Speaker Session Session in October focusing on DINOv3 and its representation alignment with the human brain!
📅 Oct 8
🕓 16:00-17:00 CET
📍 Virtual
🔗 https://ellis.eu/events/ellis-reading-group-ellisxunireps-speaker-series-session
📅 Oct 8
🕓 16:00-17:00 CET
📍 Virtual
🔗 https://ellis.eu/events/ellis-reading-group-ellisxunireps-speaker-series-session
We are thrilled to introduce the ELLIS Unireps Speaker Series! 🎉 You can nominate yourself or another researcher through the nomination form.
Stay tuned for more details! 🔵🔴
Stay tuned for more details! 🔵🔴
🔵🔴 Curious about unifying representations and sharing breakthrough ideas with fellow scientists? The ELLIS (@ellis.eu) UniReps Speaker Series is your chance to dive in!
March 3, 2025 at 10:06 AM
We are thrilled to introduce the ELLIS Unireps Speaker Series! 🎉 You can nominate yourself or another researcher through the nomination form.
Stay tuned for more details! 🔵🔴
Stay tuned for more details! 🔵🔴
🎉 The first @ellis.eu × Unireps Speaker Series (Reading Group associated with Ellis PhD & Postdoc Program) session is happening soon! 🔜
🗓️ When: 29th May 2025 – 16:30 CET
📍 Where: ethz.zoom.us/j/66426188160
🎙️ Who: Andrew Lampinen @lampinen.bsky.social (Keynote) & Jack Lindsey (Flash Talk)
🗓️ When: 29th May 2025 – 16:30 CET
📍 Where: ethz.zoom.us/j/66426188160
🎙️ Who: Andrew Lampinen @lampinen.bsky.social (Keynote) & Jack Lindsey (Flash Talk)
May 20, 2025 at 11:57 AM
🎉 The first @ellis.eu × Unireps Speaker Series (Reading Group associated with Ellis PhD & Postdoc Program) session is happening soon! 🔜
🗓️ When: 29th May 2025 – 16:30 CET
📍 Where: ethz.zoom.us/j/66426188160
🎙️ Who: Andrew Lampinen @lampinen.bsky.social (Keynote) & Jack Lindsey (Flash Talk)
🗓️ When: 29th May 2025 – 16:30 CET
📍 Where: ethz.zoom.us/j/66426188160
🎙️ Who: Andrew Lampinen @lampinen.bsky.social (Keynote) & Jack Lindsey (Flash Talk)
Next in line here at UniReps workshop is "A Framework for Standardizing Similarity Measures in a Rapidly Evolving Field", presented by @nacloss.bsky.social from MIT 🔵🔴
December 14, 2024 at 7:45 PM
Next in line here at UniReps workshop is "A Framework for Standardizing Similarity Measures in a Rapidly Evolving Field", presented by @nacloss.bsky.social from MIT 🔵🔴
🚀 Did you attend the 2nd UniReps workshop on Unifying Representations in Neural Models?
We’d love your feedback!
Take 2 minutes to fill out our form & help shape future workshops in ML, Neuroscience, & Cognitive Science.📋
docs.google.com/forms/d/e/1F...
We’d love your feedback!
Take 2 minutes to fill out our form & help shape future workshops in ML, Neuroscience, & Cognitive Science.📋
docs.google.com/forms/d/e/1F...
UniReps Workshop Feedback Form
Thank you for attending the UniReps workshop! We value your feedback to improve future events. Please take a few minutes to share your thoughts!
We thank again the generous contributions from Google ...
docs.google.com
January 9, 2025 at 2:13 PM
🚀 Did you attend the 2nd UniReps workshop on Unifying Representations in Neural Models?
We’d love your feedback!
Take 2 minutes to fill out our form & help shape future workshops in ML, Neuroscience, & Cognitive Science.📋
docs.google.com/forms/d/e/1F...
We’d love your feedback!
Take 2 minutes to fill out our form & help shape future workshops in ML, Neuroscience, & Cognitive Science.📋
docs.google.com/forms/d/e/1F...
If you are still around at #NeurIPS2024, feel free to pass by our poster at UniReps workshop @unireps.bsky.social and chat about models of continuous speech perception!
At UniReps today: Gasser Elbanna's poster "Artificial Neural Networks Generate Human-like Continuous Speech Perception". West Exhibition Hall C, B3.
Gasser built models of phoneme recognition, and finds that they replicate human confusions pretty well.
Gasser built models of phoneme recognition, and finds that they replicate human confusions pretty well.
December 14, 2024 at 3:18 PM
If you are still around at #NeurIPS2024, feel free to pass by our poster at UniReps workshop @unireps.bsky.social and chat about models of continuous speech perception!
Doors open! The UniReps × UCL NeuroAI Meetup starts now at the Sainsbury Wellcome Centre (Ground Floor Seminar Room). At 10:30, Iris Groen (UvA) kicks us off: “Alignment of visual representations in AI and human brains: beyond object recognition.” Follow for updates. #UniReps #NeuroAI #UCL
September 8, 2025 at 9:13 AM
📢 Save the date!
Join us for the next @ellis.eu x UniReps Speaker Series!
📅 27th August – 16:00 CEST
📍https://ethz.zoom.us/j/66426188160
🎙️ Speakers: Keynote by @lelandmcinnes.bsky.social & Flash Talk by Yu (Demi) Qin
🔔 Stay updated by joining our Google group: groups.google.com/u/2/g/ellis-...
Join us for the next @ellis.eu x UniReps Speaker Series!
📅 27th August – 16:00 CEST
📍https://ethz.zoom.us/j/66426188160
🎙️ Speakers: Keynote by @lelandmcinnes.bsky.social & Flash Talk by Yu (Demi) Qin
🔔 Stay updated by joining our Google group: groups.google.com/u/2/g/ellis-...
August 14, 2025 at 7:58 AM
📢 Save the date!
Join us for the next @ellis.eu x UniReps Speaker Series!
📅 27th August – 16:00 CEST
📍https://ethz.zoom.us/j/66426188160
🎙️ Speakers: Keynote by @lelandmcinnes.bsky.social & Flash Talk by Yu (Demi) Qin
🔔 Stay updated by joining our Google group: groups.google.com/u/2/g/ellis-...
Join us for the next @ellis.eu x UniReps Speaker Series!
📅 27th August – 16:00 CEST
📍https://ethz.zoom.us/j/66426188160
🎙️ Speakers: Keynote by @lelandmcinnes.bsky.social & Flash Talk by Yu (Demi) Qin
🔔 Stay updated by joining our Google group: groups.google.com/u/2/g/ellis-...
The UniReps Workshop is happening THIS SATURDAY at #NeurIPS 🤖🧠
Join us for a day of insightful talks and discussions with @sueyeonchung.bsky.social, @eringrant.bsky.social, @leavittron.bsky.social, @itsneuronal.bsky.social, @marcocuturi.bsky.social, Philip Isola, Neel Nanda and Stefanie Jegelka! 🎤
Join us for a day of insightful talks and discussions with @sueyeonchung.bsky.social, @eringrant.bsky.social, @leavittron.bsky.social, @itsneuronal.bsky.social, @marcocuturi.bsky.social, Philip Isola, Neel Nanda and Stefanie Jegelka! 🎤
December 12, 2024 at 11:41 PM
The UniReps Workshop is happening THIS SATURDAY at #NeurIPS 🤖🧠
Join us for a day of insightful talks and discussions with @sueyeonchung.bsky.social, @eringrant.bsky.social, @leavittron.bsky.social, @itsneuronal.bsky.social, @marcocuturi.bsky.social, Philip Isola, Neel Nanda and Stefanie Jegelka! 🎤
Join us for a day of insightful talks and discussions with @sueyeonchung.bsky.social, @eringrant.bsky.social, @leavittron.bsky.social, @itsneuronal.bsky.social, @marcocuturi.bsky.social, Philip Isola, Neel Nanda and Stefanie Jegelka! 🎤
UniReps will happen again this year! 🔵🔴
📢 We're thrilled to announce that the UniReps workshop will return to @NeurIPSConf 25 for its 3rd edition!
🔵Check our new Call for Papers at: unireps.org/2025/call-fo...
🔴Submit your work at: openreview.net/group?id=Neu...
See you in San Diego!🌴🇺🇸
🔵Check our new Call for Papers at: unireps.org/2025/call-fo...
🔴Submit your work at: openreview.net/group?id=Neu...
See you in San Diego!🌴🇺🇸
July 11, 2025 at 7:50 AM
UniReps will happen again this year! 🔵🔴
Excited to keep the conversation going at the NeurReps X UniReps X NeuroAI post-workshop social tn! partiful.com/e/0NoaoBepdm... @sharvaree.bsky.social @naturecomputes.bsky.social @christian-shewmake.bsky.social @unireps.bsky.social
RSVP to NEURREPS X UNIREPS X NEUROAI | Partiful
NeurReps and Unireps post workshop social - drinks and pizza social in a secret loft in gastown
Hosted by Enigma and New Theory
https://enigmaproject.ai
https://newtheory.ai
partiful.com
December 14, 2024 at 11:53 PM
Excited to keep the conversation going at the NeurReps X UniReps X NeuroAI post-workshop social tn! partiful.com/e/0NoaoBepdm... @sharvaree.bsky.social @naturecomputes.bsky.social @christian-shewmake.bsky.social @unireps.bsky.social
At UniReps today: Gasser Elbanna's poster "Artificial Neural Networks Generate Human-like Continuous Speech Perception". West Exhibition Hall C, B3.
Gasser built models of phoneme recognition, and finds that they replicate human confusions pretty well.
Gasser built models of phoneme recognition, and finds that they replicate human confusions pretty well.
December 14, 2024 at 12:50 PM
At UniReps today: Gasser Elbanna's poster "Artificial Neural Networks Generate Human-like Continuous Speech Perception". West Exhibition Hall C, B3.
Gasser built models of phoneme recognition, and finds that they replicate human confusions pretty well.
Gasser built models of phoneme recognition, and finds that they replicate human confusions pretty well.
or at the unireps workshop (unireps.org/2024/schedule).
We have a few open positions currently at MLR (Paris office) for internships, short-term post-docs, & FTE. Looking forward to the conference this year!
PS: I will bring my squash racket, LMK if you are interested in playing :)
We have a few open positions currently at MLR (Paris office) for internships, short-term post-docs, & FTE. Looking forward to the conference this year!
PS: I will bring my squash racket, LMK if you are interested in playing :)
Schedule | UniReps Workshop
Unifying Representations in Neural Models
unireps.org
December 8, 2024 at 6:02 PM
or at the unireps workshop (unireps.org/2024/schedule).
We have a few open positions currently at MLR (Paris office) for internships, short-term post-docs, & FTE. Looking forward to the conference this year!
PS: I will bring my squash racket, LMK if you are interested in playing :)
We have a few open positions currently at MLR (Paris office) for internships, short-term post-docs, & FTE. Looking forward to the conference this year!
PS: I will bring my squash racket, LMK if you are interested in playing :)
🔵🔴🎉 Stefanie Jegelka from MIT is the last speaker of our UniReps workshop, talking about "Parameter Symmetries in Neural Networks: what they affect and what to do with them"
December 14, 2024 at 11:06 PM
🔵🔴🎉 Stefanie Jegelka from MIT is the last speaker of our UniReps workshop, talking about "Parameter Symmetries in Neural Networks: what they affect and what to do with them"
For our last invited talk this morning, we are thrilled to hear @phillipisola.bsky.social from MIT present ‘The Platonic Representation Hypothesis’ at the UniReps workshop! 🎤✨
December 14, 2024 at 5:47 PM
For our last invited talk this morning, we are thrilled to hear @phillipisola.bsky.social from MIT present ‘The Platonic Representation Hypothesis’ at the UniReps workshop! 🎤✨
Why do NNs often learn similar representations? Existing identifiability results offer theoretical insights, but applying them in practice poses challenges.
We’ll present our new work exploring these challenges next week at @unireps #NeurIPS2024 🇨🇦🎉
openreview.net/pdf?id=SQKUZSieVg
1/
We’ll present our new work exploring these challenges next week at @unireps #NeurIPS2024 🇨🇦🎉
openreview.net/pdf?id=SQKUZSieVg
1/
openreview.net
December 6, 2024 at 4:06 PM
Why do NNs often learn similar representations? Existing identifiability results offer theoretical insights, but applying them in practice poses challenges.
We’ll present our new work exploring these challenges next week at @unireps #NeurIPS2024 🇨🇦🎉
openreview.net/pdf?id=SQKUZSieVg
1/
We’ll present our new work exploring these challenges next week at @unireps #NeurIPS2024 🇨🇦🎉
openreview.net/pdf?id=SQKUZSieVg
1/
We all love Wigner's classification of the Poincare group's projective unireps (i.e., particles).
I am wondering about its applicability to a world that is not Minkowski. Sure, we live in a very large mostly flat patch. But there exist e.g. black holes, so the almost-Minkowski region is finite.
I am wondering about its applicability to a world that is not Minkowski. Sure, we live in a very large mostly flat patch. But there exist e.g. black holes, so the almost-Minkowski region is finite.
October 27, 2025 at 3:35 PM
We all love Wigner's classification of the Poincare group's projective unireps (i.e., particles).
I am wondering about its applicability to a world that is not Minkowski. Sure, we live in a very large mostly flat patch. But there exist e.g. black holes, so the almost-Minkowski region is finite.
I am wondering about its applicability to a world that is not Minkowski. Sure, we live in a very large mostly flat patch. But there exist e.g. black holes, so the almost-Minkowski region is finite.
📢 We are thrilled to introduce the ELLIS (@ellis.eu) x UniReps Speaker Series!📢
🔵🔴 Each monthly session features a 40-min Keynote talk and a 20min-Flash talk.
📜 You can nominate yourself or another researcher as a speaker by filling out the nomination form: forms.gle/EbHatQW7zoVi...
🔵🔴 Each monthly session features a 40-min Keynote talk and a 20min-Flash talk.
📜 You can nominate yourself or another researcher as a speaker by filling out the nomination form: forms.gle/EbHatQW7zoVi...
April 1, 2025 at 3:48 PM
📢 We are thrilled to introduce the ELLIS (@ellis.eu) x UniReps Speaker Series!📢
🔵🔴 Each monthly session features a 40-min Keynote talk and a 20min-Flash talk.
📜 You can nominate yourself or another researcher as a speaker by filling out the nomination form: forms.gle/EbHatQW7zoVi...
🔵🔴 Each monthly session features a 40-min Keynote talk and a 20min-Flash talk.
📜 You can nominate yourself or another researcher as a speaker by filling out the nomination form: forms.gle/EbHatQW7zoVi...
Benjamin Cappell currently showcases our work "ReWaRD - Retinal Waves for Pre-Training Artificial Neural Networks mimicking Real Prenatal Development" at the UniReps Workshop at NeurIPS
@cogcovi.bsky.social
@unifau.bsky.social
github.com/BennyCa/ReWaRD
@cogcovi.bsky.social
@unifau.bsky.social
github.com/BennyCa/ReWaRD
December 15, 2023 at 4:39 PM
Benjamin Cappell currently showcases our work "ReWaRD - Retinal Waves for Pre-Training Artificial Neural Networks mimicking Real Prenatal Development" at the UniReps Workshop at NeurIPS
@cogcovi.bsky.social
@unifau.bsky.social
github.com/BennyCa/ReWaRD
@cogcovi.bsky.social
@unifau.bsky.social
github.com/BennyCa/ReWaRD
Finally, I'll be a panelist and speaker at the UniReps workshop on Friday: unireps.org
where I'll be discussing and speaking about some of the issues we've been thinking about in our recent work on representational alignment: bsky.app/profile/lamp... 4/5
where I'll be discussing and speaking about some of the issues we've been thinking about in our recent work on representational alignment: bsky.app/profile/lamp... 4/5
UniReps Workshop
Unifying Representations in Neural Models
unireps.org
December 8, 2023 at 7:55 PM
Finally, I'll be a panelist and speaker at the UniReps workshop on Friday: unireps.org
where I'll be discussing and speaking about some of the issues we've been thinking about in our recent work on representational alignment: bsky.app/profile/lamp... 4/5
where I'll be discussing and speaking about some of the issues we've been thinking about in our recent work on representational alignment: bsky.app/profile/lamp... 4/5
🔵🔴We’re hosting a UniReps Workshop social🌟🥳
📍 Location: Moose's Down Under Bar & Grill, Vancouver
🗓️ Date & Time: Saturday, Dec 14 | 5:45 PM
Don’t miss the chance to connect, relax, and have some fun. See you there! 🔵🔴
📍 Location: Moose's Down Under Bar & Grill, Vancouver
🗓️ Date & Time: Saturday, Dec 14 | 5:45 PM
Don’t miss the chance to connect, relax, and have some fun. See you there! 🔵🔴
December 10, 2024 at 10:46 PM
🔵🔴We’re hosting a UniReps Workshop social🌟🥳
📍 Location: Moose's Down Under Bar & Grill, Vancouver
🗓️ Date & Time: Saturday, Dec 14 | 5:45 PM
Don’t miss the chance to connect, relax, and have some fun. See you there! 🔵🔴
📍 Location: Moose's Down Under Bar & Grill, Vancouver
🗓️ Date & Time: Saturday, Dec 14 | 5:45 PM
Don’t miss the chance to connect, relax, and have some fun. See you there! 🔵🔴
Research in mechanistic interpretability and neuroscience often relies on interpreting internal representations to understand systems, or manipulating representations to improve models. I gave a talk at the UniReps workshop at NeurIPS on a few challenges for this area. Summary thread: 1/
December 22, 2023 at 1:54 AM
Research in mechanistic interpretability and neuroscience often relies on interpreting internal representations to understand systems, or manipulating representations to improve models. I gave a talk at the UniReps workshop at NeurIPS on a few challenges for this area. Summary thread: 1/
Up next at UniReps × UCL NeuroAI: two short talks 👇
🎙️ Loek van Rossem (Gatsby, UCL): "When Representations Align: Universality in Representation Learning Dynamics"
🎙️ Austin Meek (MLATS / Univ. of Delaware): "Inducing Human-like Biases in Moral Reasoning Language Models"
#UniReps #NeuroAI #UCL
🎙️ Loek van Rossem (Gatsby, UCL): "When Representations Align: Universality in Representation Learning Dynamics"
🎙️ Austin Meek (MLATS / Univ. of Delaware): "Inducing Human-like Biases in Moral Reasoning Language Models"
#UniReps #NeuroAI #UCL
September 8, 2025 at 11:01 AM