Dongwon Han
@dwhan89.bsky.social
Data Scientist | Retired Astrophysicist
Currently thinking about RL, Optimization, and Computing
Currently thinking about RL, Optimization, and Computing
Reposted by Dongwon Han
Academia’s fountain of youth: students are referred to as Kids, if you’re under 50 you’re a Young Investigator, and it’s illegal to update the labs’ profile pictures
January 3, 2025 at 7:59 AM
Academia’s fountain of youth: students are referred to as Kids, if you’re under 50 you’re a Young Investigator, and it’s illegal to update the labs’ profile pictures
Reposted by Dongwon Han
Introducing ASAL: Automating the Search for Artificial Life with Foundation Models
Blog: sakana.ai/asal/
We propose a new method called Automated Search for Artificial Life (ASAL) which uses foundation models to automate the discovery of the most interesting and open-ended artificial lifeforms!
Blog: sakana.ai/asal/
We propose a new method called Automated Search for Artificial Life (ASAL) which uses foundation models to automate the discovery of the most interesting and open-ended artificial lifeforms!
December 24, 2024 at 2:58 AM
Introducing ASAL: Automating the Search for Artificial Life with Foundation Models
Blog: sakana.ai/asal/
We propose a new method called Automated Search for Artificial Life (ASAL) which uses foundation models to automate the discovery of the most interesting and open-ended artificial lifeforms!
Blog: sakana.ai/asal/
We propose a new method called Automated Search for Artificial Life (ASAL) which uses foundation models to automate the discovery of the most interesting and open-ended artificial lifeforms!
Reposted by Dongwon Han
Now also out on Arxiv:
www.arxiv.org/abs/2412.12119
www.arxiv.org/abs/2412.12119
December 18, 2024 at 8:23 AM
Now also out on Arxiv:
www.arxiv.org/abs/2412.12119
www.arxiv.org/abs/2412.12119
Reposted by Dongwon Han
Awesome stuff!
Introducing MASt3R-SLAM, the first real-time monocular dense SLAM with MASt3R as a foundation.
Easy to use like DUSt3R/MASt3R, from an uncalibrated RGB video it recovers accurate, globally consistent poses & a dense map.
With @ericdexheimer.bsky.social* @ajdavison.bsky.social (*Equal Contribution)
Easy to use like DUSt3R/MASt3R, from an uncalibrated RGB video it recovers accurate, globally consistent poses & a dense map.
With @ericdexheimer.bsky.social* @ajdavison.bsky.social (*Equal Contribution)
December 17, 2024 at 1:39 PM
Awesome stuff!
Reposted by Dongwon Han
📚🧵1/7 It is finally here!! Only one more week until the print release of our textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” with @mitpress.bsky.social!
What you get, why you should be interested and more, all below in a short 🧵👇
What you get, why you should be interested and more, all below in a short 🧵👇
December 9, 2024 at 6:34 PM
📚🧵1/7 It is finally here!! Only one more week until the print release of our textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” with @mitpress.bsky.social!
What you get, why you should be interested and more, all below in a short 🧵👇
What you get, why you should be interested and more, all below in a short 🧵👇
Reposted by Dongwon Han
After two years, our paper on generative models for structure-based drug design is finally out in @natcomputsci.bsky.social
www.nature.com/articles/s43...
www.nature.com/articles/s43...
Structure-based drug design with equivariant diffusion models - Nature Computational Science
This work applies diffusion models to conditional molecule generation and shows how they can be used to tackle various structure-based drug design problems
www.nature.com
December 9, 2024 at 2:00 PM
After two years, our paper on generative models for structure-based drug design is finally out in @natcomputsci.bsky.social
www.nature.com/articles/s43...
www.nature.com/articles/s43...
Reposted by Dongwon Han
🔵AVAILABLE NOW: Multiagent Reinforcement Learning Course
This course, organised by the IIIA, was given by
Stefano V. Albrecht last September. We hope you find it useful and that you can enjoy and learn as much as we did.
▶️Playlist course: youtube.com/playlist?lis...
This course, organised by the IIIA, was given by
Stefano V. Albrecht last September. We hope you find it useful and that you can enjoy and learn as much as we did.
▶️Playlist course: youtube.com/playlist?lis...
December 4, 2024 at 12:24 PM
🔵AVAILABLE NOW: Multiagent Reinforcement Learning Course
This course, organised by the IIIA, was given by
Stefano V. Albrecht last September. We hope you find it useful and that you can enjoy and learn as much as we did.
▶️Playlist course: youtube.com/playlist?lis...
This course, organised by the IIIA, was given by
Stefano V. Albrecht last September. We hope you find it useful and that you can enjoy and learn as much as we did.
▶️Playlist course: youtube.com/playlist?lis...
Reposted by Dongwon Han
Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.
December 4, 2024 at 4:01 PM
Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.
Reposted by Dongwon Han
Tomorrow at 6 PM UTC, Yaqi Duan will talk about "Taming « data-hungry » RL? Stability in continuous state-action spaces".
December 2, 2024 at 10:38 AM
Tomorrow at 6 PM UTC, Yaqi Duan will talk about "Taming « data-hungry » RL? Stability in continuous state-action spaces".
Reposted by Dongwon Han
Reposted by Dongwon Han
Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition!
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
November 27, 2024 at 9:00 AM
Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition!
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423