Winfried Ripken
@winfried-ripken.bsky.social
PhD Student @TU Berlin @BIFOLD working on ML applications for chemistry
November 28, 2025 at 11:39 AM
✨ Via a modular architecture, we enable a fair comparison of symmetries changing both attention mechanism and embedding strategies of our model
✨ We transfer the powerful DiT architecture from Computer Vision to the molecular domain, proposing two complementary graph-based conditioning strategies
✨ We transfer the powerful DiT architecture from Computer Vision to the molecular domain, proposing two complementary graph-based conditioning strategies
November 28, 2025 at 11:39 AM
✨ Via a modular architecture, we enable a fair comparison of symmetries changing both attention mechanism and embedding strategies of our model
✨ We transfer the powerful DiT architecture from Computer Vision to the molecular domain, proposing two complementary graph-based conditioning strategies
✨ We transfer the powerful DiT architecture from Computer Vision to the molecular domain, proposing two complementary graph-based conditioning strategies
We introduce DiTMC, a new way to predict molecular conformers - the different 3D shapes molecules can flex into.
✨ We learn to predict 3D geometry from molecular structure
✨ We achieve state-of-the-art results on the GEOM benchmarks
✨ We learn to predict 3D geometry from molecular structure
✨ We achieve state-of-the-art results on the GEOM benchmarks
November 28, 2025 at 11:39 AM
We introduce DiTMC, a new way to predict molecular conformers - the different 3D shapes molecules can flex into.
✨ We learn to predict 3D geometry from molecular structure
✨ We achieve state-of-the-art results on the GEOM benchmarks
✨ We learn to predict 3D geometry from molecular structure
✨ We achieve state-of-the-art results on the GEOM benchmarks