The thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), held in New Orleans, drew to a close on Saturday 16 December. In this post, we take a look at what participants got up to during the last few...
The thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), held in New Orleans, drew to a close on Saturday 16 December. In this post, we take a look at what participants got up to during the last few days of the conference. You can find part one of our round-up here.
This is my attempt to convey how unreasonable and unimaginably large #NeurIPS2023 is. Wild. pic.twitter.com/Fl89mI3wGy
— Micah Bowles @ NeurIPS (@Micah_mb010) December 14, 2023
@samianholt's work shows that observing at regular time intervals is NOT optimal in certain continuous-time environments, while irregular observations yield higher expected utility…what you should definitely observe is him at #NeurIPS2023 & how we tackle this important problem! pic.twitter.com/VVsQe0pfVP
— Mihaela van der Schaar (@MihaelaVDS) December 14, 2023
So excited to be part of the Intrinsically Motivated Open-Ended Learning workshop at #NeurIPS2023! First up: Doina Precup sketches out a general blueprint for continual reinforcement learning.
More details on today’s workshop here: https://t.co/u8kcGBQseW pic.twitter.com/0kaGTSnlH8
— Natalia Vélez (natvelali @ 
/
/fediscience.org) (@natvelali) December 16, 2023
Join us at poster #112, 5pm-7pm at #NeurIPS2023, where we will present our new dataset on wildfire spread prediction: WildfireSpreadTS.
It's useful for spatio-temporal modeling, working with noisy labels, high-dimensional data and class-imbalance.https://t.co/BQhwyhpfR3 pic.twitter.com/R890oGeiRz
— Sebastian Gerard (@GracefulGerard) December 14, 2023
Congratulations to @MicheleGaribbo from @BristolUni for your work on reducing the variance in TD learning. #NeurIPS2023 pic.twitter.com/MPR53mJVyY
— Lucia Cipolina Kun (@LuciaCKun) December 14, 2023
Ever wondered how we can use AI and geometry to potentially accelerate vaccine discovery? 
We use the power of equivariance to predict the binding between antigens and antibodies.
Come to our poster at the @neur_reps
workshop #NeurIPS2023 pic.twitter.com/MTS39Iq6l8
— Clémentine Dominé @NeurIPS 
(@ClementineDomi6) December 16, 2023
Super excited to be presenting the TS-DiffuGen poster at the #NeurIPS2023 workshop on diffusion models tomorrow! TS-DiffuGen uses a 3D reactant/product coordinate-conditioned diffusion model to generate accurate reaction Transition State conformations! pic.twitter.com/7g8YVAFTZQ
— Sacha Raffaud (@sacha_rfd) December 14, 2023
Sitting on the floor in the PACKED LLM session at #NeurIPS2023
= 
= 
pic.twitter.com/6GJAA8z7FB
— Han Spinner (@H__Spinner) December 14, 2023
I gave a keynote this week at the fantastic ATTRIB Workshop #NeurIPS2023
"What does scale give us: Why we are building a ladder 
to the moon 
"
Some of you asked for my slides, sharing below:https://t.co/qBlINJfi0y
Thanks to the organizers for a fantastic workshop! 
— Sara Hooker (@sarahookr) December 17, 2023
The last panel I attended featured @huggingface researchers, academic experts, Elham from @NIST and @rajiinio. The exchange between Margaret and Rayid was as informative as watching Deb play the role of a peacemaker. Thanks to the panelists for the session. #NeurIPS2023 pic.twitter.com/b0ho3TT9mO
— Michael Akinwumi (@datawumi) December 17, 2023
Attending NeurIPS Workshops? Do not miss the 3rd ENLSP on Efficient LLM and Speech models happening on Saturday Dec. 16th, (Room 206-207 & virtual). #NeurIPS2023 7 Keynote Speakers, A Panel, 10 Spotlight talks & 70+ Posters.
Link: https://t.co/KtfTeMBQ7f pic.twitter.com/2G2Y7MhAhb
— Mehdi Rezagholizadeh (@mrgzadeh) December 15, 2023
I had a great time at #NeurIPS2023. And I met a lot of researchers who I have known online for a long time. I am so excited that I could catch up with the researchers from different fields. It’s also a great opportunity for me to know more about the advance of Graph modeling. pic.twitter.com/WBjy2kUBMu
— Hezhe Qiao (@qiaohezhe) December 17, 2023
Honored to receive best paper for MPP at the @AI_for_Science @NeurIPSConf workshop with my teammates @PolymathicAI! Thanks to everyone who stopped by our poster for the great discussions and to the organizers for running such an interesting workshop! #AI4Science #NeurIPS2023 https://t.co/rr3Oepp3ky
— Mike McCabe (@mikemccabe210) December 17, 2023
I had **the best time** at #NeurIPS2023–more fun than I've ever had–and bummed it's over.
If you're a tech minority, maybe you can come next year? It will be in Vancouver, Canada.
Below, I'll detail themes where it seems the majority of research comes from tech minorities:
— MMitchell @ NeurIPS (@mmitchell_ai) December 17, 2023
Deep dive into 4 NeurIPS 2023 best paper award winners: https://t.co/zfc0awC1IE
– Are Emergent Abilities of Large Language Models a Mirage? https://t.co/WB10lJ1yYf
– Scaling Data-Constrained Language Models. https://t.co/OMeehH8AMP
– Direct Preference Optimization: Your… pic.twitter.com/lpPyIN47pu
— Sophia Yang, Ph.D. (@sophiamyang) December 17, 2023
Next up: Our second panel of the day focuses on local and indigenous knowledge systems. #NeurIPS2023 pic.twitter.com/Cw9YYTcRSS
— Climate Change AI (@ClimateChangeAI) December 16, 2023
Seen at NeurIPS 
pic.twitter.com/4ruAhR6t95
— Alexander Terenin @NeurIPS (@avt_im) December 15, 2023
#NeurIPS2023 dinner with my team and collaborators. Great to get everyone together after an energizing week! pic.twitter.com/CtpfV0rZpe
— Prof. Anima Anandkumar (@AnimaAnandkumar) December 16, 2023