Today (Wednesday) at #NeurIPS2024 our group members will be presenting the following papers:
December 11, 2024 at 6:40 PM
Today (Wednesday) at #NeurIPS2024 our group members will be presenting the following papers:
En route Vancouver to attend #NeurIPS2024 and excited to be a part of the following papers 👇!
I am also recruiting multiple PhD students for Fall '25. DM me here or on Whova, if interested in: multilinguality, personalized alignment, real use inspired evals (see website in bio for details).
I am also recruiting multiple PhD students for Fall '25. DM me here or on Whova, if interested in: multilinguality, personalized alignment, real use inspired evals (see website in bio for details).
December 9, 2024 at 7:03 PM
En route Vancouver to attend #NeurIPS2024 and excited to be a part of the following papers 👇!
I am also recruiting multiple PhD students for Fall '25. DM me here or on Whova, if interested in: multilinguality, personalized alignment, real use inspired evals (see website in bio for details).
I am also recruiting multiple PhD students for Fall '25. DM me here or on Whova, if interested in: multilinguality, personalized alignment, real use inspired evals (see website in bio for details).
Interested in amortization + experimental design + decision making? #NeurIPS2024
Come by to our poster, starting soon (11-2, East Hall)!
NeurIPS link: neurips.cc/virtual/2024...
Paper: openreview.net/forum?id=zBG...
with @huangdaolang.bsky.social Yujia Guo @samikaski.bsky.social
Come by to our poster, starting soon (11-2, East Hall)!
NeurIPS link: neurips.cc/virtual/2024...
Paper: openreview.net/forum?id=zBG...
with @huangdaolang.bsky.social Yujia Guo @samikaski.bsky.social
December 13, 2024 at 5:53 PM
Interested in amortization + experimental design + decision making? #NeurIPS2024
Come by to our poster, starting soon (11-2, East Hall)!
NeurIPS link: neurips.cc/virtual/2024...
Paper: openreview.net/forum?id=zBG...
with @huangdaolang.bsky.social Yujia Guo @samikaski.bsky.social
Come by to our poster, starting soon (11-2, East Hall)!
NeurIPS link: neurips.cc/virtual/2024...
Paper: openreview.net/forum?id=zBG...
with @huangdaolang.bsky.social Yujia Guo @samikaski.bsky.social
Josh Tenenbaum on scaling up vs growing up and the path to human-like reasoning #NeurIPS2024
December 15, 2024 at 6:14 PM
Josh Tenenbaum on scaling up vs growing up and the path to human-like reasoning #NeurIPS2024
If you’re at #Neurips2024 next week, come meet us in poster session 3 on Thu 12 Dec 11 a.m!
Or at our oral presentation during the @neur_reps workshop on Saturday 14th!
Paper: arxiv.org/abs/2312.06386
Github: github.com/cedricrommel...
Or at our oral presentation during the @neur_reps workshop on Saturday 14th!
Paper: arxiv.org/abs/2312.06386
Github: github.com/cedricrommel...
December 4, 2024 at 8:00 AM
If you’re at #Neurips2024 next week, come meet us in poster session 3 on Thu 12 Dec 11 a.m!
Or at our oral presentation during the @neur_reps workshop on Saturday 14th!
Paper: arxiv.org/abs/2312.06386
Github: github.com/cedricrommel...
Or at our oral presentation during the @neur_reps workshop on Saturday 14th!
Paper: arxiv.org/abs/2312.06386
Github: github.com/cedricrommel...
Excited to share "Dense Associative Memory through the Lens of Random Features" accepted to #neurips2024🎉
DenseAMs need new weights for each stored pattern–hurting scalability. Kernel methods let us add memories without adding weights!
Distributed memory for DenseAMs, unlocked🔓
DenseAMs need new weights for each stored pattern–hurting scalability. Kernel methods let us add memories without adding weights!
Distributed memory for DenseAMs, unlocked🔓
December 3, 2024 at 4:33 PM
Excited to share "Dense Associative Memory through the Lens of Random Features" accepted to #neurips2024🎉
DenseAMs need new weights for each stored pattern–hurting scalability. Kernel methods let us add memories without adding weights!
Distributed memory for DenseAMs, unlocked🔓
DenseAMs need new weights for each stored pattern–hurting scalability. Kernel methods let us add memories without adding weights!
Distributed memory for DenseAMs, unlocked🔓
If you're attending, come check out our posters or feel free to reach out to connect during the conference!
Looking forward to insightful conversations and connecting with everyone; See you all at NeurIPS!
#NeurIPS2024 #NIPS24 #MachineLearning #DiffusionModels #Research #AI
Looking forward to insightful conversations and connecting with everyone; See you all at NeurIPS!
#NeurIPS2024 #NIPS24 #MachineLearning #DiffusionModels #Research #AI
December 12, 2024 at 6:28 AM
If you're attending, come check out our posters or feel free to reach out to connect during the conference!
Looking forward to insightful conversations and connecting with everyone; See you all at NeurIPS!
#NeurIPS2024 #NIPS24 #MachineLearning #DiffusionModels #Research #AI
Looking forward to insightful conversations and connecting with everyone; See you all at NeurIPS!
#NeurIPS2024 #NIPS24 #MachineLearning #DiffusionModels #Research #AI
last_day == best_day @neuripsconf.bsky.social
The @workshopmlsb.bsky.social is about to start and GIFFLAR will be presented in the poster sessions.
Come for some sweets to the East Meeting Rooms 11 and 12. Poster sessions are at 11:20am and 4pm.
@dbojar.bsky.social #mlsb #NeurIPS2024 #glycotime
The @workshopmlsb.bsky.social is about to start and GIFFLAR will be presented in the poster sessions.
Come for some sweets to the East Meeting Rooms 11 and 12. Poster sessions are at 11:20am and 4pm.
@dbojar.bsky.social #mlsb #NeurIPS2024 #glycotime
December 15, 2024 at 4:26 PM
last_day == best_day @neuripsconf.bsky.social
The @workshopmlsb.bsky.social is about to start and GIFFLAR will be presented in the poster sessions.
Come for some sweets to the East Meeting Rooms 11 and 12. Poster sessions are at 11:20am and 4pm.
@dbojar.bsky.social #mlsb #NeurIPS2024 #glycotime
The @workshopmlsb.bsky.social is about to start and GIFFLAR will be presented in the poster sessions.
Come for some sweets to the East Meeting Rooms 11 and 12. Poster sessions are at 11:20am and 4pm.
@dbojar.bsky.social #mlsb #NeurIPS2024 #glycotime
Check out the work our lab in Copenhagen will be presenting at #NeurIPS2024 🌟
@neuripsconf.bsky.social @belongielab.org
@neuripsconf.bsky.social @belongielab.org
With @neuripsconf.bsky.social right around the corner, we’re excited to be presenting our work soon! Here’s an overview
(1/5)
(1/5)
December 3, 2024 at 11:49 AM
Check out the work our lab in Copenhagen will be presenting at #NeurIPS2024 🌟
@neuripsconf.bsky.social @belongielab.org
@neuripsconf.bsky.social @belongielab.org
The problem with current SSL? It's hungry. Very hungry. 🤖
Training time: Weeks
Dataset size: Millions of images
Compute costs: 💸💸💸
Our #NeurIPS2024 poster makes SSL pipelines 2x faster and achieves similar accuracy at 50% pretraining cost! 💪🏼✨
🧵 1/8
Training time: Weeks
Dataset size: Millions of images
Compute costs: 💸💸💸
Our #NeurIPS2024 poster makes SSL pipelines 2x faster and achieves similar accuracy at 50% pretraining cost! 💪🏼✨
🧵 1/8
December 13, 2024 at 3:44 AM
The problem with current SSL? It's hungry. Very hungry. 🤖
Training time: Weeks
Dataset size: Millions of images
Compute costs: 💸💸💸
Our #NeurIPS2024 poster makes SSL pipelines 2x faster and achieves similar accuracy at 50% pretraining cost! 💪🏼✨
🧵 1/8
Training time: Weeks
Dataset size: Millions of images
Compute costs: 💸💸💸
Our #NeurIPS2024 poster makes SSL pipelines 2x faster and achieves similar accuracy at 50% pretraining cost! 💪🏼✨
🧵 1/8
December 10, 2024 at 6:48 PM
I'll be at #NeurIPS2024 next week, and would be happy to chat about deep learning architectures, sequence modeling, reasoning, neuroscience, world models, graphs, and almost anything :)
I also will be presenting Chimera (a 2D SSM) on Wednesday (4:30 PM).
I also will be presenting Chimera (a 2D SSM) on Wednesday (4:30 PM).
December 5, 2024 at 8:43 PM
I'll be at #NeurIPS2024 next week, and would be happy to chat about deep learning architectures, sequence modeling, reasoning, neuroscience, world models, graphs, and almost anything :)
I also will be presenting Chimera (a 2D SSM) on Wednesday (4:30 PM).
I also will be presenting Chimera (a 2D SSM) on Wednesday (4:30 PM).
🪐 Bing Liu from the University of Illinois at Chicago gave a great talk on Continual Learning with Large Language Models.
Timestamp 7:08:17 in neurips.cc/virtual/2024...
#NeurIPS2024 #AdaptiveFoundationModels
Timestamp 7:08:17 in neurips.cc/virtual/2024...
#NeurIPS2024 #AdaptiveFoundationModels
December 19, 2024 at 4:59 AM
🪐 Bing Liu from the University of Illinois at Chicago gave a great talk on Continual Learning with Large Language Models.
Timestamp 7:08:17 in neurips.cc/virtual/2024...
#NeurIPS2024 #AdaptiveFoundationModels
Timestamp 7:08:17 in neurips.cc/virtual/2024...
#NeurIPS2024 #AdaptiveFoundationModels
I couldn't be happier! Preparing the trip to #NeurIPS2024 we received the notification of acceptance of our paper in #COLING2025 with Paula Ontalvilla and Aitor Ormazabal. Paula has just started with her PhD at @hitz-zentroa.bsky.social and she is already publishing at this level!
December 2, 2024 at 9:21 AM
I couldn't be happier! Preparing the trip to #NeurIPS2024 we received the notification of acceptance of our paper in #COLING2025 with Paula Ontalvilla and Aitor Ormazabal. Paula has just started with her PhD at @hitz-zentroa.bsky.social and she is already publishing at this level!
We spy @f-immorlano.bsky.social + LEAP alum Sungduk Yu, who supported @juannat7.bsky.social @ #NeurIPS2024: "ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction."
#NSF #CUSEAS
@neuripsconf.bsky.social
@columbiaclimate.bsky.social
@ucirvine.bsky.social
#NSF #CUSEAS
@neuripsconf.bsky.social
@columbiaclimate.bsky.social
@ucirvine.bsky.social
December 14, 2024 at 6:00 PM
We spy @f-immorlano.bsky.social + LEAP alum Sungduk Yu, who supported @juannat7.bsky.social @ #NeurIPS2024: "ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction."
#NSF #CUSEAS
@neuripsconf.bsky.social
@columbiaclimate.bsky.social
@ucirvine.bsky.social
#NSF #CUSEAS
@neuripsconf.bsky.social
@columbiaclimate.bsky.social
@ucirvine.bsky.social
Meanwhile, @juannat7.bsky.social has Vancouver covered at @neuripsconf.bsky.social w/"ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction!"
Check out the presentation + poster: https://buff.ly/4ff6xAs
@neuripsconf.bsky.social #NeurIPS2024
Check out the presentation + poster: https://buff.ly/4ff6xAs
@neuripsconf.bsky.social #NeurIPS2024
NeurIPS 2024
The NeurIPS Logo above may be used on presentations. Right-click and choose download. It is a vector graphic and may be used at any scale.
buff.ly
December 13, 2024 at 8:00 PM
Meanwhile, @juannat7.bsky.social has Vancouver covered at @neuripsconf.bsky.social w/"ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction!"
Check out the presentation + poster: https://buff.ly/4ff6xAs
@neuripsconf.bsky.social #NeurIPS2024
Check out the presentation + poster: https://buff.ly/4ff6xAs
@neuripsconf.bsky.social #NeurIPS2024
5/ See the preprint for more details: arxiv.org/abs/2410.08710
And come and talk to us at our poster at #NeurIPS2024 @neuripsconf.bsky.social , both Petrus and I will be there!
Wed, Dec 11, 11:00 PST -- Poster Session 1 East
And come and talk to us at our poster at #NeurIPS2024 @neuripsconf.bsky.social , both Petrus and I will be there!
Wed, Dec 11, 11:00 PST -- Poster Session 1 East
Preferential Normalizing Flows
Eliciting a high-dimensional probability distribution from an expert via noisy judgments is notoriously challenging, yet useful for many applications, such as prior elicitation and reward modeling. We...
arxiv.org
December 4, 2024 at 9:06 AM
5/ See the preprint for more details: arxiv.org/abs/2410.08710
And come and talk to us at our poster at #NeurIPS2024 @neuripsconf.bsky.social , both Petrus and I will be there!
Wed, Dec 11, 11:00 PST -- Poster Session 1 East
And come and talk to us at our poster at #NeurIPS2024 @neuripsconf.bsky.social , both Petrus and I will be there!
Wed, Dec 11, 11:00 PST -- Poster Session 1 East
Pleased to present our poster at #NeurIPS2024 workshop on Bayesian Decisionmaking and Uncertainty! 🎉 Our work explores using large language models for eliciting expert-informed Bayesian priors. Elicited lots of discussion with the ML community too! Check it out: neurips.cc/virtual/2024...
December 20, 2024 at 12:43 PM
Pleased to present our poster at #NeurIPS2024 workshop on Bayesian Decisionmaking and Uncertainty! 🎉 Our work explores using large language models for eliciting expert-informed Bayesian priors. Elicited lots of discussion with the ML community too! Check it out: neurips.cc/virtual/2024...
Hello #vancouver! Let's have a good #neurips2024 conference this week
December 10, 2024 at 12:59 AM
Hello #vancouver! Let's have a good #neurips2024 conference this week
Great to see a strong @helmholtzai.bsky.social presence at #NeurIPS2024
Gooooood morning, Vancouver! ☀️ It's the first day of the
@neuripsconf.bsky.social 2024, and we are excited to share the strong presence of Helmholtz AI researchers in Canada for the next 5 days - find the abstracts of work to be showcased below:
www.helmholtz.ai/detail/helmh...
@neuripsconf.bsky.social 2024, and we are excited to share the strong presence of Helmholtz AI researchers in Canada for the next 5 days - find the abstracts of work to be showcased below:
www.helmholtz.ai/detail/helmh...
Helmholtz AI @ NeurIPS 2024: an overview
The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024) is set to take place at the Vancouver Convention
www.helmholtz.ai
December 10, 2024 at 10:10 PM
Great to see a strong @helmholtzai.bsky.social presence at #NeurIPS2024
📢 Another paper at #NeurIPS2024!
📰 "FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning"
Read it here: arxiv.org/abs/2407.13711
Details in 🧵
📰 "FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning"
Read it here: arxiv.org/abs/2407.13711
Details in 🧵
FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
Laplace approximations are popular techniques for endowing deep networks with epistemic uncertainty estimates as they can be applied without altering the predictions of the trained network, and they s...
arxiv.org
December 12, 2024 at 11:47 AM
📢 Another paper at #NeurIPS2024!
📰 "FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning"
Read it here: arxiv.org/abs/2407.13711
Details in 🧵
📰 "FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning"
Read it here: arxiv.org/abs/2407.13711
Details in 🧵
Image from MIT Professor Rosalind Picard’s keynote at #NeurIPS2024, showing how problematic you can be when working on topics like AI Ethics without an intersectional mindset. It’s funny she chose to share a student’s nationality but nothing else… Photo credit: Zhengzhong Tu
December 14, 2024 at 9:00 PM
Image from MIT Professor Rosalind Picard’s keynote at #NeurIPS2024, showing how problematic you can be when working on topics like AI Ethics without an intersectional mindset. It’s funny she chose to share a student’s nationality but nothing else… Photo credit: Zhengzhong Tu
🚨 Thrilled to share that Compositional Generalization Across Distributional Shifts with Sparse Tree Operations received a spotlight award at #NeurIPS2024! 🌟 I'll present a poster on Tuesday and give an invited lightning talk at the System 2 Reasoning Workshop on Sunday. 🧵👇
December 9, 2024 at 3:06 PM
🚨 Thrilled to share that Compositional Generalization Across Distributional Shifts with Sparse Tree Operations received a spotlight award at #NeurIPS2024! 🌟 I'll present a poster on Tuesday and give an invited lightning talk at the System 2 Reasoning Workshop on Sunday. 🧵👇
Check out this super interesting poster by Sergio Calo and Gergely Neu at #NeurIPS2024 !
curious how to compute couplings between Markov chains living on different spaces?
we got what you need (and more) in our
paper "Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently". come check out the poster at 11am, dec 11!
arxiv.org/abs/2406.04056
we got what you need (and more) in our
paper "Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently". come check out the poster at 11am, dec 11!
arxiv.org/abs/2406.04056
December 3, 2024 at 9:56 AM
Check out this super interesting poster by Sergio Calo and Gergely Neu at #NeurIPS2024 !