Sign in

Giannis Daras

@giannisdaras.bsky.social
119 followers 15 following 13 posts

@MIT Postdoctoral Researcher.

PostsRepliesMedia
Giannis Daras @giannisdaras.bsky.social · 08/07/2025
Announcing Ambient Protein Diffusion, a state-of-the-art 17M-params generative model for protein structures. Diversity improves by 91% and designability by 26% over the previous 200M SOTA model for long proteins. The trick? Treat low pLDDT AlphaFold predictions as low-quality data.
110
Reposted by Giannis Daras
AI x Bio Discovery @aixbiobot.bsky.social · 06/07/2025
Ambient Proteins: Training Diffusion Models on Low Quality Structures [new] Trains diffusion models using low-confidence AlphaFold2 structures by adapting the diffusion objective based on corruption level.
Figure 1Figure 2Figure 3Figure 4
041
Reposted by Giannis Daras
lebellig @lebellig.bsky.social · 07/07/2025
New episode in this line of work from @giannisdaras.bsky.social et al. on training diffusion models with mostly bad/low-quality/corrupted data (+few high-quality samples). This time for proteins! 📄 Ambient diffusion Omni: arxiv.org/pdf/2506.10038 📄 Ambient Proteins: www.biorxiv.org/content/10.1...
132
Reposted by Giannis Daras
Alex Dimakis @alexdimakis.bsky.social · 12/02/2025
We are releasing OpenThinker-32B, the best 32B reasoning model with open data. We match or outperform Deepseek-R1-32B (a closed data model) in reasoning benchmarks. Congrats to Negin and the whole Open Thoughts team. github.com/open-thought...
Performance of the best known Reasoning models on various Benchmarks. OpenThinker-32B matches the current state of the art.
3268
Reposted by Giannis Daras
Dimitris Papailiopoulos @dimitrisp.bsky.social · 13/02/2025
o3 can't multiply beyond a few digits... But I think multiplication, addition, maze solving and easy-to-hard generalization is actually solvable on standard transformers... with recursive self-improvement Below is the acc of a tiny model teaching itself how to add and multiply
2214
Giannis Daras @giannisdaras.bsky.social · 20/12/2024
Well deserved!
010
Reposted by Giannis Daras
Peyman Milanfar @docmilanfar.bsky.social · 14/12/2024
Did Gauss invent the Gaussian? - Laplace wrote down the integral first in 1783 - Gauss then described it in 1809 in the context of least-sq. for astronomical measurements - Pearson & Fisher framed it as ‘normal’ density only in 1910 * Best part is: Gauss gave Laplace credit!
0385
Reposted by Giannis Daras
Peyman Milanfar @docmilanfar.bsky.social · 04/12/2024
“There is nothing quite so useless, as doing with great efficiency, something that should not be done at all.”
16512
Reposted by Giannis Daras
Peyman Milanfar @docmilanfar.bsky.social · 27/11/2024
“To write well is to think clearly.”
1423
Giannis Daras @giannisdaras.bsky.social · 24/11/2024
Please reply to your ICLR rebuttals 🙏
000