Thread by @PrescientDesign

We're excited to have a number of papers by co-authors at Prescient and @genentech Research Bio AI/ML at #ICLR2023, #ICML23, and #AISTATS2023 spanning topics from basic ML to applications in drug discovery and even on the properties of black holes! 🌌 Check out below 👇 1/9

"Towards Understanding and Improving GFlowNet Training" #ICML23

@maxwshen, @folinoid, @EhsanHRA, @loukasa_tweet, @kchonyc, @tbyanc

2/9

"Few-shot Learning of Abstract Geometric Reasoning by Infusing Lattice Symmetry Priors in Attention Mechanisms" #ICML23

Matti Atzeni, @mrinmayasachan, @loukasa_tweet

3/9

"Bayesian Optimization with Conformal Prediction Sets" #AISTATS2023

arxiv.org/abs/2210.12496

@samuel_stanton_, Wesley Maddox, @andrewgwils

4/9

"Retrospective Uncertainties for Deep Models using Vine Copulas" #AISTATS2023

arxiv.org/abs/2302.12606

@tagasovska, @Firat_Ozdemir, @AxelBrando_

5/9

"Latent SDEs for Modelling Quasar Variability and Inferring Black Hole Properties" (Spotlight) #ICLR2023 #Physics4ML

openreview.net/pdf?id=x2NOLHC…

@joshua_fagin, @jiwoncpark, Henry Best, @saavikford, Matthew J Graham, Ashley Villar, @cosmo_shirley, James Chan, @matt_of_earth

6/9

"Learning protein family manifolds with smoothed energy-based models" (Spotlight) #ICLR2023 #Physics4ML and @MLDD_Workshop

openreview.net/pdf?id=IilnB8j…

@nc_frey, @dabkiel1, Joseph Kleinhenz, et al.

7/9

"SupSiam: Non-contrastive Auxiliary Loss for Learning from Molecular Conformers" #ICLR2023 @MLDD_Workshop

arxiv.org/abs/2302.07754

Michael Maser, @jiwoncpark, @joshualin24, @jaehyeon_lee_ml, @nc_frey, @amw_stanford

8/9

"Improving Graph Generation by Restricting Graph Bandwidth" #ICLR2023 @MLDD_Workshop

arxiv.org/abs/2301.10857

Nathaniel Diamant, @alexmtseng, @kangway, @tbyanc, @gabo_scalia

9/9