194 citations · 466 across the 25 of their papers we have counts for
26 papers
ARGUS: Visualization of AI-Assisted Task Guidance in AR
Sonia Castelo, Joao Rulff, Erin McGowan +15
The concept of augmented reality (AR) assistants has captured the human imagination for decades, becoming a staple of modern science fiction. To pursue this goal, it is necessary t…
Active and Passive Causal Inference Learning
Daniel Jiwoong Im, Kyunghyun Cho
This paper serves as a starting point for machine learning researchers, engineers and students who are interested in but not yet familiar with causal inference. We start by laying…
AbDiffuser: Full-Atom Generation of in vitro Functioning Antibodies
Karolis Martinkus, Jan Ludwiczak, Kyunghyun Cho +8
We introduce AbDiffuser, an equivariant and physics-informed diffusion model for the joint generation of antibody 3D structures and sequences. AbDiffuser is built on top of a new r…
Protein Discovery with Discrete Walk-Jump Sampling
Nathan C. Frey, Daniel Berenberg, Karina Zadorozhny +10
We resolve difficulties in training and sampling from a discrete generative model by learning a smoothed energy function, sampling from the smoothed data manifold with Langevin Mar…
BOtied: Multi-objective Bayesian optimization with tied multivariate ranks
Ji Won Park, Nataša Tagasovska, Michael Maser +2
Many scientific and industrial applications require the joint optimization of multiple, potentially competing objectives. Multi-objective Bayesian optimization (MOBO) is a sample-e…
Towards Understanding and Improving GFlowNet Training
Max W. Shen, Emmanuel Bengio, Ehsan Hajiramezanali +3
Generative flow networks (GFlowNets) are a family of algorithms that learn a generative policy to sample discrete objects with non-negative reward . Learning objectives g…
Protein Design with Guided Discrete Diffusion
Nate Gruver, Samuel Stanton, Nathan C. Frey +6
A popular approach to protein design is to combine a generative model with a discriminative model for conditional sampling. The generative model samples plausible sequences while t…
Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction
Grace Yang, Ming Cao, Lavender Y. Jiang +6
Traditional evaluation metrics for classification in natural language processing such as accuracy and area under the curve fail to differentiate between models with different predi…
A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences
Nataša Tagasovska, Nathan C. Frey, Andreas Loukas +9
Deep generative models have emerged as a popular machine learning-based approach for inverse design problems in the life sciences. However, these problems often require sampling ne…
PropertyDAG: Multi-objective Bayesian optimization of partially ordered, mixed-variable properties for biological sequence design
Ji Won Park, Samuel Stanton, Saeed Saremi +6
Bayesian optimization offers a sample-efficient framework for navigating the exploration-exploitation trade-off in the vast design space of biological sequences. Whereas it is poss…
Endowing Language Models with Multimodal Knowledge Graph Representations
Ningyuan Huang, Yash R. Deshpande, Yibo Liu +4
We propose a method to make natural language understanding models more parameter efficient by storing knowledge in an external knowledge graph (KG) and retrieving from this KG usin…
Multi-segment preserving sampling for deep manifold sampler
Daniel Berenberg, Jae Hyeon Lee, Simon Kelow +6
Deep generative modeling for biological sequences presents a unique challenge in reconciling the bias-variance trade-off between explicit biological insight and model flexibility.…
Linear Connectivity Reveals Generalization Strategies
Jeevesh Juneja, Rachit Bansal, Kyunghyun Cho +2
It is widely accepted in the mode connectivity literature that when two neural networks are trained similarly on the same data, they are connected by a path through parameter space…
Translation between Molecules and Natural Language
Carl Edwards, Tuan Lai, Kevin Ros +3
We present a self-supervised learning framework for pretraining models on a vast amount of unlabeled natural language text and molecule strings. $\textbf{MolT5…
Generative multitask learning mitigates target-causing confounding
Taro Makino, Krzysztof J. Geras, Kyunghyun Cho
We propose generative multitask learning (GMTL), a simple and scalable approach to causal representation learning for multitask learning. Our approach makes a minor change to the c…
Causal Scene BERT: Improving object detection by searching for challenging groups of data
Cinjon Resnick, Or Litany, Amlan Kar +4
Modern computer vision applications rely on learning-based perception modules parameterized with neural networks for tasks like object detection. These modules frequently have low…
Causal Effect Variational Autoencoder with Uniform Treatment
Daniel Jiwoong Im, Kyunghyun Cho, Narges Razavian
Domain adaptation and covariate shift are big issues in deep learning and they ultimately affect any causal inference algorithms that rely on deep neural networks. Causal effect va…
Chemical-Reaction-Aware Molecule Representation Learning
Hongwei Wang, Weijiang Li, Xiaomeng Jin +4
Molecule representation learning (MRL) methods aim to embed molecules into a real vector space. However, existing SMILES-based (Simplified Molecular-Input Line-Entry System) or GNN…
An Empirical Study on Few-shot Knowledge Probing for Pretrained Language Models
Tianxing He, Kyunghyun Cho, James Glass
Prompt-based knowledge probing for 1-hop relations has been used to measure how much world knowledge is stored in pretrained language models. Existing work uses considerable amount…
Meta-repository of screening mammography classifiers
Benjamin Stadnick, Jan Witowski, Vishwaesh Rajiv +4
Artificial intelligence (AI) is showing promise in improving clinical diagnosis. In breast cancer screening, recent studies show that AI has the potential to improve early cancer d…
Mode recovery in neural autoregressive sequence modeling
Ilia Kulikov, Sean Welleck, Kyunghyun Cho
Despite its wide use, recent studies have revealed unexpected and undesirable properties of neural autoregressive sequence models trained with maximum likelihood, such as an unreas…
Comparing Test Sets with Item Response Theory
Clara Vania, Phu Mon Htut, William Huang +6
Recent years have seen numerous NLP datasets introduced to evaluate the performance of fine-tuned models on natural language understanding tasks. Recent results from large pretrain…
True Few-Shot Learning with Language Models
Ethan Perez, Douwe Kiela, Kyunghyun Cho
Pretrained language models (LMs) perform well on many tasks even when learning from a few examples, but prior work uses many held-out examples to tune various aspects of learning,…
KLUE: Korean Language Understanding Evaluation
Sungjoon Park, Jihyung Moon, Sungdong Kim +28
We introduce Korean Language Understanding Evaluation (KLUE) benchmark. KLUE is a collection of 8 Korean natural language understanding (NLU) tasks, including Topic Classification,…