Krzysztof Maziarz
@maziarz.bsky.social
Principal Researcher at Microsoft Research AI for Science, ML for Drug Discovery, ex Google AI & tensorflight
If this sounds interesting and you happen to be at #NeurIPS2024, come to the MSR booth at 5PM today for talk and Q&A about this work!
December 11, 2024 at 9:30 PM
If this sounds interesting and you happen to be at #NeurIPS2024, come to the MSR booth at 5PM today for talk and Q&A about this work!
In blind comparisons by chemists, the two modules were judged on a similar level, but Chimera was clearly preferred 🧑🔬
December 11, 2024 at 9:30 PM
In blind comparisons by chemists, the two modules were judged on a similar level, but Chimera was clearly preferred 🧑🔬
If you compare the performance of the two modules that are part of Chimera, either can end up on top depending on e.g. how common the ground-truth transformation is.
But Chimera outperforms both across the board ✨️
But Chimera outperforms both across the board ✨️
December 11, 2024 at 9:30 PM
If you compare the performance of the two modules that are part of Chimera, either can end up on top depending on e.g. how common the ground-truth transformation is.
But Chimera outperforms both across the board ✨️
But Chimera outperforms both across the board ✨️
To our knowledge, we're the first to show large gains from ensembling in this domain.
The trick is to combine full ranked output lists using a strategy based on learning-to-rank.
Gives a significant improvement out-of-the-box for any pair of models 🔥
The trick is to combine full ranked output lists using a strategy based on learning-to-rank.
Gives a significant improvement out-of-the-box for any pair of models 🔥
December 11, 2024 at 9:30 PM
To our knowledge, we're the first to show large gains from ensembling in this domain.
The trick is to combine full ranked output lists using a strategy based on learning-to-rank.
Gives a significant improvement out-of-the-box for any pair of models 🔥
The trick is to combine full ranked output lists using a strategy based on learning-to-rank.
Gives a significant improvement out-of-the-box for any pair of models 🔥
ML for Drug Discovery at MSR here ⚗️
December 7, 2024 at 10:00 AM
ML for Drug Discovery at MSR here ⚗️