Chaitanya K. Joshi
@chaitjo.bsky.social
PhD student at University of Cambridge. Intern at FAIR, Meta & Prescient Design, Genentech. Deep Learning for Biomolecule Design.
https://chaitjo.com
https://chaitjo.com
And at big industrial labs with large budgets, the scientists are just able to do a lot more intuition-building. They are able to try ideas a lot faster, and get a 'feel' for what ideas will work much faster as a result.
October 18, 2025 at 5:30 AM
And at big industrial labs with large budgets, the scientists are just able to do a lot more intuition-building. They are able to try ideas a lot faster, and get a 'feel' for what ideas will work much faster as a result.
It can train foundation models, but can it train frontier models too? ;)
August 16, 2025 at 5:21 AM
It can train foundation models, but can it train frontier models too? ;)
Great image of organizers space group symmetry!
August 5, 2025 at 7:25 AM
Great image of organizers space group symmetry!
Alex’s explainer thread is a heartfelt one: x.com/Alex__Abruda...
And the preprint is on arXiv link: www.arxiv.org/abs/2507.21938
And the preprint is on arXiv link: www.arxiv.org/abs/2507.21938
x.com
July 31, 2025 at 6:11 PM
Alex’s explainer thread is a heartfelt one: x.com/Alex__Abruda...
And the preprint is on arXiv link: www.arxiv.org/abs/2507.21938
And the preprint is on arXiv link: www.arxiv.org/abs/2507.21938
LLMs transfer knowledge across domains; eg. doing well on maths translates to getting better at programming, too.
Molecular models often don't - We may need unified representations for true generalization.
Molecular models often don't - We may need unified representations for true generalization.
July 16, 2025 at 10:25 AM
LLMs transfer knowledge across domains; eg. doing well on maths translates to getting better at programming, too.
Molecular models often don't - We may need unified representations for true generalization.
Molecular models often don't - We may need unified representations for true generalization.