@gregorlied

CS student @ TU Berlin. ML for molecular simulation @ml_tuberlin.

 Berlin, Germany
gregorlied.github.io/
Joined August 2020
  • Tweets5
  • Following126
  • Followers19
1Media
Excited to share our latest work on large-timestep molecular dynamics.
Winfried Ripken@RipkenWinfriedFeb 19
Ever get tired of tiny timesteps bottlenecking your MD simulations? We show how to train a model for large-timestep Hamiltonian dynamics directly on standard MLFF datasets. ๐—ก๐—ผ ๐—ฟ๐—ฒ๐—ณ๐—ฒ๐—ฟ๐—ฒ๐—ป๐—ฐ๐—ฒ ๐˜๐—ฟ๐—ฎ๐—ท๐—ฒ๐—ฐ๐˜๐—ผ๐—ฟ๐—ถ๐—ฒ๐˜€, ๐—ป๐—ผ ๐˜‚๐—ป๐—ฟ๐—ผ๐—น๐—น๐—ถ๐—ป๐—ด, ๐—ป๐—ผ ๐˜๐—ฒ๐—ฎ๐—ฐ๐—ต๐—ฒ๐—ฟ needed!๐Ÿงต๐Ÿ‘‡
2
191
Excited to be at ICML with @michaelplainer & @gregorlied to present our ๐ŸŒŸ spotlight ๐ŸŒŸ paper on Hamiltonian Flow Maps for large-timestep molecular dynamics! Come say hi at our poster tomorrow or send us a message if you want to chat! ๐Ÿค— ๐Ÿ—“๏ธ July 8, 10:30 AM โ€“ 12:15 PM ๐Ÿ“ #1306
2
10
1
110
8,180
Heading to @NeurIPSConf in SD! ๐Ÿš€ Weโ€™ll be presenting our latest work, DiTMC - a modular architecture for molecular conformer generation. ๐Ÿ–๏ธ Excited to meet new and old friends! If you want to grab a coffee and chat about generative models & AI4Science, feel free to reach out.
2
1
130
๐Ÿ“„ย arxiv.org/abs/2506.15378 ๐Ÿ”—ย github.com/ML4MolSim/dit_mc ๐Ÿ“†ย Thursday 4 Dec, 11am - 2pm, Exhibit Hall C,D,E #1709

Sampling 3D Molecular Conformers with Diffusion Transformers

Diffusion Transformers (DiTs) have demonstrated strong performance in generative modeling, particularly in image synthesis, making them a compelling choice for molecular conformer generation....

arxiv.org
1
85
๐Ÿ™ย This is a joint work with the amazing @FrankThorben, @RipkenWinfried, Klaus-Robert Mรผller, Oliver T. Unke and Stefan Chmiela. Thank you so much for this fantastic collaboration!
82
Load more