🎉 Excited to have had the opportunity to present two posters at the ICLR2025 workshops! 🖼️🖼️
A big thanks to my coauthors and to everyone who dropped by to discuss!
Also, thanks to the Re-Align and DeLTa organizers for hosting such an inspiring workshop day. ✨
@bifold.berlin @tuberlin.bsky.social
A big thanks to my coauthors and to everyone who dropped by to discuss!
Also, thanks to the Re-Align and DeLTa organizers for hosting such an inspiring workshop day. ✨
@bifold.berlin @tuberlin.bsky.social
May 3, 2025 at 9:21 AM
🎉 Excited to have had the opportunity to present two posters at the ICLR2025 workshops! 🖼️🖼️
A big thanks to my coauthors and to everyone who dropped by to discuss!
Also, thanks to the Re-Align and DeLTa organizers for hosting such an inspiring workshop day. ✨
@bifold.berlin @tuberlin.bsky.social
A big thanks to my coauthors and to everyone who dropped by to discuss!
Also, thanks to the Re-Align and DeLTa organizers for hosting such an inspiring workshop day. ✨
@bifold.berlin @tuberlin.bsky.social
Excited to be joining the panel discussion later today! ✨
Mark your calendars! 📅 The @WiMLWorkshop Social returns to @iclrconf!
🗓️ Friday, April 25th, 2025
⏰ 12:30 PM - 2:00 PM
📍 Hall 1 Apex, Singapore Expo
iclr.cc/virtual/2025...
lu.ma/ftdnjnf9
#ICLR2025
Mark your calendars! 📅 The @WiMLWorkshop Social returns to @iclrconf!
🗓️ Friday, April 25th, 2025
⏰ 12:30 PM - 2:00 PM
📍 Hall 1 Apex, Singapore Expo
iclr.cc/virtual/2025...
lu.ma/ftdnjnf9
#ICLR2025
April 25, 2025 at 12:34 AM
Excited to be joining the panel discussion later today! ✨
Mark your calendars! 📅 The @WiMLWorkshop Social returns to @iclrconf!
🗓️ Friday, April 25th, 2025
⏰ 12:30 PM - 2:00 PM
📍 Hall 1 Apex, Singapore Expo
iclr.cc/virtual/2025...
lu.ma/ftdnjnf9
#ICLR2025
Mark your calendars! 📅 The @WiMLWorkshop Social returns to @iclrconf!
🗓️ Friday, April 25th, 2025
⏰ 12:30 PM - 2:00 PM
📍 Hall 1 Apex, Singapore Expo
iclr.cc/virtual/2025...
lu.ma/ftdnjnf9
#ICLR2025
I’ll be presenting our work ✨VocADT, tomorrow at #ICLR2025
Check out our poster session: iclr.cc/virtual/2025...
🗓️Thu 24 Apr 3 p.m. - 5:30 p.m
📍Hall 3 + Hall 2B #250
So excited to be attending @iclr_conf in Singapore 🇸🇬!
Check out our poster session: iclr.cc/virtual/2025...
🗓️Thu 24 Apr 3 p.m. - 5:30 p.m
📍Hall 3 + Hall 2B #250
So excited to be attending @iclr_conf in Singapore 🇸🇬!
April 23, 2025 at 10:02 AM
I’ll be presenting our work ✨VocADT, tomorrow at #ICLR2025
Check out our poster session: iclr.cc/virtual/2025...
🗓️Thu 24 Apr 3 p.m. - 5:30 p.m
📍Hall 3 + Hall 2B #250
So excited to be attending @iclr_conf in Singapore 🇸🇬!
Check out our poster session: iclr.cc/virtual/2025...
🗓️Thu 24 Apr 3 p.m. - 5:30 p.m
📍Hall 3 + Hall 2B #250
So excited to be attending @iclr_conf in Singapore 🇸🇬!
Not in Singapore for #ICLR2025 but our lab’s work is! In particular, I am very proud of these collaborations:
✨INCLUDE (spotlight) — models fail to grasp regional nuances across languages
💎To Code or Not to Code (poster) — code is key for generalizing beyond coding tasks
✨INCLUDE (spotlight) — models fail to grasp regional nuances across languages
💎To Code or Not to Code (poster) — code is key for generalizing beyond coding tasks
April 22, 2025 at 8:15 AM
Not in Singapore for #ICLR2025 but our lab’s work is! In particular, I am very proud of these collaborations:
✨INCLUDE (spotlight) — models fail to grasp regional nuances across languages
💎To Code or Not to Code (poster) — code is key for generalizing beyond coding tasks
✨INCLUDE (spotlight) — models fail to grasp regional nuances across languages
💎To Code or Not to Code (poster) — code is key for generalizing beyond coding tasks
Sad to miss #ICLR2025 this year, but my amazing co-authors will be there in person to present Pangea!
neulab.github.io/Pangea/
I’ll be at the Foundation Models for Science conference at Simons Foundation, NYC next week, then heading to NAACL (more details soon).
Let’s catch up if you’re around!✨
neulab.github.io/Pangea/
I’ll be at the Foundation Models for Science conference at Simons Foundation, NYC next week, then heading to NAACL (more details soon).
Let’s catch up if you’re around!✨
April 22, 2025 at 12:42 AM
Sad to miss #ICLR2025 this year, but my amazing co-authors will be there in person to present Pangea!
neulab.github.io/Pangea/
I’ll be at the Foundation Models for Science conference at Simons Foundation, NYC next week, then heading to NAACL (more details soon).
Let’s catch up if you’re around!✨
neulab.github.io/Pangea/
I’ll be at the Foundation Models for Science conference at Simons Foundation, NYC next week, then heading to NAACL (more details soon).
Let’s catch up if you’re around!✨
I will be presenting this ✨ spotlight 💫 paper at #ICLR2025 with @martinagvilas.bsky.social. Come say hi if you're interested in DNN circuits, complexity and #interpretability
📆 Poster Session 4 (#530)
🕰️ Fri 25 Apr. 3:00-5:30 PM
📝 openreview.net/forum?id=Qog...
📊 iclr.cc/virtual/2025...
📆 Poster Session 4 (#530)
🕰️ Fri 25 Apr. 3:00-5:30 PM
📝 openreview.net/forum?id=Qog...
📊 iclr.cc/virtual/2025...
April 18, 2025 at 6:33 PM
I will be presenting this ✨ spotlight 💫 paper at #ICLR2025 with @martinagvilas.bsky.social. Come say hi if you're interested in DNN circuits, complexity and #interpretability
📆 Poster Session 4 (#530)
🕰️ Fri 25 Apr. 3:00-5:30 PM
📝 openreview.net/forum?id=Qog...
📊 iclr.cc/virtual/2025...
📆 Poster Session 4 (#530)
🕰️ Fri 25 Apr. 3:00-5:30 PM
📝 openreview.net/forum?id=Qog...
📊 iclr.cc/virtual/2025...
New in our #ICLR2025 spotlight ✨, we introduce PGPCA, a Probabilistic Geometric method that enables modeling and dimensionality reduction for data distributed around nonlinear manifolds. We also show PGPCA’s application to brain data.
👏 Han-Lin Hsieh
@iclr-conf.bsky.social
Paper, Code, 🧵⬇️
👏 Han-Lin Hsieh
@iclr-conf.bsky.social
Paper, Code, 🧵⬇️
April 17, 2025 at 6:55 PM
New in our #ICLR2025 spotlight ✨, we introduce PGPCA, a Probabilistic Geometric method that enables modeling and dimensionality reduction for data distributed around nonlinear manifolds. We also show PGPCA’s application to brain data.
👏 Han-Lin Hsieh
@iclr-conf.bsky.social
Paper, Code, 🧵⬇️
👏 Han-Lin Hsieh
@iclr-conf.bsky.social
Paper, Code, 🧵⬇️
✨Contrastive Learning from Synthetic Audio Doppelgängers #ICLR2025✨ w/
@nikhilsinghmus.bsky.social
Our method learns useful audio representations with randomly synthesized sounds (often better than real data!)
🌐Project: doppelgangers.media.mit.edu
📄Paper: arxiv.org/abs/2406.05923
🧵1/3
@nikhilsinghmus.bsky.social
Our method learns useful audio representations with randomly synthesized sounds (often better than real data!)
🌐Project: doppelgangers.media.mit.edu
📄Paper: arxiv.org/abs/2406.05923
🧵1/3
March 12, 2025 at 8:25 PM
✨Contrastive Learning from Synthetic Audio Doppelgängers #ICLR2025✨ w/
@nikhilsinghmus.bsky.social
Our method learns useful audio representations with randomly synthesized sounds (often better than real data!)
🌐Project: doppelgangers.media.mit.edu
📄Paper: arxiv.org/abs/2406.05923
🧵1/3
@nikhilsinghmus.bsky.social
Our method learns useful audio representations with randomly synthesized sounds (often better than real data!)
🌐Project: doppelgangers.media.mit.edu
📄Paper: arxiv.org/abs/2406.05923
🧵1/3
我々の新しい知識蒸留の手法「TAID」の論文が #ICLR2025 でSpotlight (Top 5%)を受賞しました。✨
openreview.net/forum?id=cqs...
bsky.app/profile/saka...
openreview.net/forum?id=cqs...
bsky.app/profile/saka...
“TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models” has been accepted at #ICLR2025 as a Spotlight Paper ✨
Blog post (English): sakana.ai/taid/
Paper (OpenReview): openreview.net/forum?id=cqs...
Blog post (English): sakana.ai/taid/
Paper (OpenReview): openreview.net/forum?id=cqs...
February 16, 2025 at 8:18 AM
我々の新しい知識蒸留の手法「TAID」の論文が #ICLR2025 でSpotlight (Top 5%)を受賞しました。✨
openreview.net/forum?id=cqs...
bsky.app/profile/saka...
openreview.net/forum?id=cqs...
bsky.app/profile/saka...
“TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models” has been accepted at #ICLR2025 as a Spotlight Paper ✨
Blog post (English): sakana.ai/taid/
Paper (OpenReview): openreview.net/forum?id=cqs...
Blog post (English): sakana.ai/taid/
Paper (OpenReview): openreview.net/forum?id=cqs...
February 12, 2025 at 4:14 PM
“TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models” has been accepted at #ICLR2025 as a Spotlight Paper ✨
Blog post (English): sakana.ai/taid/
Paper (OpenReview): openreview.net/forum?id=cqs...
Blog post (English): sakana.ai/taid/
Paper (OpenReview): openreview.net/forum?id=cqs...
🔥 How can large language models revolutionize protein design?
At #LMRL #ICLR2025, we’ll host Alex Rives (split between MIT, BroadInstitute & EvolutionaryScale), who led Meta AI’s protein folding team. He’ll share insights on AI-driven evolutionary-scale protein modeling! 🧬✨ #AI #Biotech
At #LMRL #ICLR2025, we’ll host Alex Rives (split between MIT, BroadInstitute & EvolutionaryScale), who led Meta AI’s protein folding team. He’ll share insights on AI-driven evolutionary-scale protein modeling! 🧬✨ #AI #Biotech
February 10, 2025 at 2:00 PM
✨ The VIS Lab at the #University of #Amsterdam is proud and excited to announce it has #TWELVE papers 🚀 accepted for the leading #AI-#makers conference on representation learning ( #ICLR2025 ) in Singapore 🇸🇬. 1/n
👇👇👇 @ellisamsterdam.bsky.social
👇👇👇 @ellisamsterdam.bsky.social
February 3, 2025 at 7:44 AM
✨ The VIS Lab at the #University of #Amsterdam is proud and excited to announce it has #TWELVE papers 🚀 accepted for the leading #AI-#makers conference on representation learning ( #ICLR2025 ) in Singapore 🇸🇬. 1/n
👇👇👇 @ellisamsterdam.bsky.social
👇👇👇 @ellisamsterdam.bsky.social
At this year’s #NAACL2025 in Albuquerque 🌵 and #ICLR2025 in Singapore 🌏, three papers have been accepted to both Main Conference Proceedings! 📝✨ Plus, exciting papers in Findings as well! 🚀📚
(1/🧵)
(1/🧵)
January 27, 2025 at 11:03 AM
At this year’s #NAACL2025 in Albuquerque 🌵 and #ICLR2025 in Singapore 🌏, three papers have been accepted to both Main Conference Proceedings! 📝✨ Plus, exciting papers in Findings as well! 🚀📚
(1/🧵)
(1/🧵)
✨✨ 2 papers accepted to #ICLR2025!! Hoping our work can move us a little closer to autonomous scientific discovery! 🧬🥼
DiscoveryBench (openreview.net/forum?id=vyf...)
Searching for Optimal Solutions with LLMs via Bayesian Optimization (openreview.net/forum?id=aVf...)
DiscoveryBench (openreview.net/forum?id=vyf...)
Searching for Optimal Solutions with LLMs via Bayesian Optimization (openreview.net/forum?id=aVf...)
January 26, 2025 at 9:42 AM
✨✨ 2 papers accepted to #ICLR2025!! Hoping our work can move us a little closer to autonomous scientific discovery! 🧬🥼
DiscoveryBench (openreview.net/forum?id=vyf...)
Searching for Optimal Solutions with LLMs via Bayesian Optimization (openreview.net/forum?id=aVf...)
DiscoveryBench (openreview.net/forum?id=vyf...)
Searching for Optimal Solutions with LLMs via Bayesian Optimization (openreview.net/forum?id=aVf...)
Two papers accepted at ICLR 2025 focusing on **rank-adaptive** PEFT with LoRA-like adapters. Exciting! 🎉🚀
Grateful to my amazing co-authors and looking forward to presenting these works! 💡✨ #ICLR2025 @iclr-conf.bsky.social
Details in the threads 👇
Grateful to my amazing co-authors and looking forward to presenting these works! 💡✨ #ICLR2025 @iclr-conf.bsky.social
Details in the threads 👇
January 26, 2025 at 7:52 AM
Two papers accepted at ICLR 2025 focusing on **rank-adaptive** PEFT with LoRA-like adapters. Exciting! 🎉🚀
Grateful to my amazing co-authors and looking forward to presenting these works! 💡✨ #ICLR2025 @iclr-conf.bsky.social
Details in the threads 👇
Grateful to my amazing co-authors and looking forward to presenting these works! 💡✨ #ICLR2025 @iclr-conf.bsky.social
Details in the threads 👇
Excited to share that we have two papers accepted to #ICLR2025 #ICLR!
One of them:
🧠 "Overcoming Slow Decision Frequencies in Continuous Control"
✨ Brain-inspired, model-based Sequence RL achieving SOTA performance at human-level decision speeds!
#ReinforcementLearning #AI
One of them:
🧠 "Overcoming Slow Decision Frequencies in Continuous Control"
✨ Brain-inspired, model-based Sequence RL achieving SOTA performance at human-level decision speeds!
#ReinforcementLearning #AI
January 24, 2025 at 7:08 PM
Excited to share that we have two papers accepted to #ICLR2025 #ICLR!
One of them:
🧠 "Overcoming Slow Decision Frequencies in Continuous Control"
✨ Brain-inspired, model-based Sequence RL achieving SOTA performance at human-level decision speeds!
#ReinforcementLearning #AI
One of them:
🧠 "Overcoming Slow Decision Frequencies in Continuous Control"
✨ Brain-inspired, model-based Sequence RL achieving SOTA performance at human-level decision speeds!
#ReinforcementLearning #AI
🎉🎉 Our paper just got accepted to #ICLR2025! 🎉🎉
Byte-level LLMs without training and guaranteed performance? Curious how? Dive into our work! 📚✨
Paper: arxiv.org/abs/2410.09303
Github: github.com/facebookrese...
Byte-level LLMs without training and guaranteed performance? Curious how? Dive into our work! 📚✨
Paper: arxiv.org/abs/2410.09303
Github: github.com/facebookrese...
January 22, 2025 at 8:57 PM
🎉🎉 Our paper just got accepted to #ICLR2025! 🎉🎉
Byte-level LLMs without training and guaranteed performance? Curious how? Dive into our work! 📚✨
Paper: arxiv.org/abs/2410.09303
Github: github.com/facebookrese...
Byte-level LLMs without training and guaranteed performance? Curious how? Dive into our work! 📚✨
Paper: arxiv.org/abs/2410.09303
Github: github.com/facebookrese...
Accepted at #ICLR2025✨
🧐Which languages benefit the most from vocabulary adaptation?
We introduce VocADT, a new vocabulary adaptation method with a vocabulary adapter.
We explore the impact of various adaptation strategies on languages with diverse scripts and fragmentation to answer this question
🧐Which languages benefit the most from vocabulary adaptation?
We introduce VocADT, a new vocabulary adaptation method with a vocabulary adapter.
We explore the impact of various adaptation strategies on languages with diverse scripts and fragmentation to answer this question
January 22, 2025 at 7:27 PM
Accepted at #ICLR2025✨
🧐Which languages benefit the most from vocabulary adaptation?
We introduce VocADT, a new vocabulary adaptation method with a vocabulary adapter.
We explore the impact of various adaptation strategies on languages with diverse scripts and fragmentation to answer this question
🧐Which languages benefit the most from vocabulary adaptation?
We introduce VocADT, a new vocabulary adaptation method with a vocabulary adapter.
We explore the impact of various adaptation strategies on languages with diverse scripts and fragmentation to answer this question
🚨 1 month to go! 🚨
The submission deadline for the AI4NA workshop at @iclr-conf.bsky.social is fast approaching! 🧬
✨ Submissions on OpenReview will open soon—stay tuned! ✨
🔗 Learn more on our web page (link below 👇)
#AI4NA #ICLR2025
The submission deadline for the AI4NA workshop at @iclr-conf.bsky.social is fast approaching! 🧬
✨ Submissions on OpenReview will open soon—stay tuned! ✨
🔗 Learn more on our web page (link below 👇)
#AI4NA #ICLR2025
January 3, 2025 at 2:49 PM
🚨 1 month to go! 🚨
The submission deadline for the AI4NA workshop at @iclr-conf.bsky.social is fast approaching! 🧬
✨ Submissions on OpenReview will open soon—stay tuned! ✨
🔗 Learn more on our web page (link below 👇)
#AI4NA #ICLR2025
The submission deadline for the AI4NA workshop at @iclr-conf.bsky.social is fast approaching! 🧬
✨ Submissions on OpenReview will open soon—stay tuned! ✨
🔗 Learn more on our web page (link below 👇)
#AI4NA #ICLR2025