The prediction of molecular properties is a crucial task in the field of...
Length generalization, the ability to generalize from small training con...
Auditing unwanted social bias in language models (LMs) is inherently har...
Efficient transfer learning algorithms are key to the success of foundat...
Protein language models (PLMs) pre-trained on large-scale protein sequen...
Pre-training methods on proteins are recently gaining interest, leveragi...
With the advancements in machine learning (ML) methods and compute resou...
Machine Learning-guided solutions for protein learning tasks have made
s...
In this work we propose a novel end-to-end multi-stage Knowledge Graph (...
The demonstrated success of transfer learning has popularized approaches...
Generative Flow Networks (GFlowNets) have demonstrated significant
perfo...
We introduce equi-tuning, a novel fine-tuning method that transforms
(po...
Recent success in fine-tuning large models, that are pretrained on broad...
Inverse protein folding, i.e., designing sequences that fold into a give...
With the prospect of automating a number of chemical tasks with high
fid...
Consider K processes, each generating a sequence of identical and
indepe...
Training generative models that capture rich semantics of the data and
i...
With the growing availability of data within various scientific domains,...
Massive molecular simulations of drug-target proteins have been used as ...
The COVID-19 pandemic has highlighted the urgency for developing more
ef...
The problem of molecular generation has received significant attention
r...
Learning effective protein representations is critical in a variety of t...
Optimization of real-world black-box functions defined over purely
categ...
Photo-acid generators (PAGs) are compounds that release acids (H^+ ions)...
This paper investigates the problem of best arm identification in
contam...
Computational protein design, i.e. inferring novel and diverse protein
s...
We present a "physics-enhanced deep-surrogate ("PEDS") approach towards
...
Automatic construction of relevant Knowledge Bases (KBs) from text, and
...
Current methods for viral discovery target evolutionarily conserved prot...
Designing novel protein sequences for a desired 3D topological fold is a...
Predicting chemical properties from the structure of a molecule is of gr...
The field of Deep Learning is rich with empirical evidence of human-like...
Deep generative models have emerged as a powerful tool for learning
info...
The field of Deep Learning is rich with empirical evidence of human-like...
Deep generative models, such as Variational Autoencoders (VAEs), have be...
Enhancing model robustness under new and even adversarial environments i...
Recent advancements in transfer learning have made it a promising approa...
Machine learning has shown potential for optimizing existing molecules w...
In this work, we present a dual learning approach for unsupervised text ...
Deep generative models are increasingly becoming integral parts of the i...
Chemical toxicity prediction using machine learning is important in drug...
The loss landscapes of deep neural networks are not well understood due ...
Surrogate models for partial-differential equations are widely used in t...
We consider the problem of black-box function optimization over the bool...
De novo therapeutic design is challenged by a vast chemical repertoire a...
Generative feature matching network (GFMN) is an approach for training
i...
Mode connectivity provides novel geometric insights on analyzing loss
la...
The recent COVID-19 pandemic has highlighted the need for rapid therapeu...
Decentralized Parallel SGD (D-PSGD) and its asynchronous variant Asynchr...
Adaptive gradient algorithms perform gradient-based updates using the hi...