Aligning large language models (LLMs) with human values and intents
crit...
Modeling weather and climate is an essential endeavor to understand the ...
The goal of offline black-box optimization (BBO) is to optimize an expen...
Reinforcement learning presents an attractive paradigm to reason about
s...
The goal of multi-objective reinforcement learning (MORL) is to learn
po...
Multimodal contrastive pretraining has been used to train multimodal
rep...
Recent research on robustness has revealed significant performance gaps
...
Most state-of-the-art approaches for weather and climate modeling are ba...
We are interested in learning scalable agents for reinforcement learning...
Natural agents can effectively learn from multiple data sources that dif...
The goal of offline reinforcement learning (RL) is to learn near-optimal...
Continuous Normalizing Flows (CNFs) are a class of generative models tha...
Neural Processes (NPs) are a popular class of approaches for meta-learni...
Many problems in science and engineering involve optimizing an expensive...
Recent advances in contrastive representation learning over paired image...
The goal of imitation learning is to mimic expert behavior from
demonstr...
We are interested in training general-purpose reinforcement learning age...
Recent work has shown that offline reinforcement learning (RL) can be
fo...
While neural networks have shown remarkable success on classification ta...
A structural equation model (SEM) is an effective framework to reason ov...
We are interested in learning generative models for complex geometries
d...
We introduce the "inverse bandit" problem of estimating the rewards of a...
Progress towards the energy breakthroughs needed to combat climate chang...
We present a framework that abstracts Reinforcement Learning (RL) as a
s...
The goal of Multi-task Bayesian Optimization (MBO) is to minimize the nu...
We investigate the capability of a transformer pretrained on natural lan...
A key challenge with machine learning approaches for ranking is the gap
...
The objective of lifelong reinforcement learning (RL) is to optimize age...
Learning generative models for graph-structured data is challenging beca...
Real-world datasets are often biased with respect to key demographic fac...
A learned generative model often produces biased statistics relative to ...
Given unpaired data from multiple domains, a key challenge is to efficie...
Sorting input objects is an important step in many machine learning
pipe...
The goal of statistical compressive sensing is to efficiently acquire an...
Learning data representations that are transferable and fair with respec...
Several algorithms for solving constraint satisfaction problems are base...
In compressed sensing, a small number of linear measurements can be used...
Modeling agent behavior is central to understanding the emergence of com...
Learning latent variable models with stochastic variational inference is...
We propose a generalization of the best arm identification problem in
st...
Graphs are a fundamental abstraction for modeling relational data. Howev...
Evaluating the performance of generative models for unsupervised learnin...
We propose a new approach for using unsupervised boosting to create an
e...
Prediction tasks over nodes and edges in networks require careful effort...
An important approach for efficient inference in probabilistic graphical...