The availability of large pre-trained models is changing the landscape of Machine Learning
research and practice, moving from a" training from scratch" to a" fine-tuning''paradigm …

We propose a general and scalable approximate sampling strategy for probabilistic models
with discrete variables. Our approach uses gradients of the likelihood function with respect …

A well-calibrated neural model produces confidence (probability outputs) closely
approximated by the expected accuracy. While prior studies have shown that mixup training …

Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from
relatively little experience and the ability to learn policies that generalize to a range of …

Multilingual pre-trained Large Language Models (LLMs) are incredibly effective at Question
Answering (QA), a core task in Natural Language Understanding, achieving high accuracies …

Though pre-trained language models achieve notable success in many applications, it's
usually controversial for over-confident predictions. Specifically, the in-distribution (ID) …

Abstract Energy-Based Models (EBMs) are an important class of probabilistic models, also
known as random fields and undirected graphical models. EBMs are un-normalized and …

In the age of information overload, people's information needs from long documents are
rapidly emerging, while people's patience for careful reading and reasoning is gradually …

Reinforcement learning has shown great promise in aligning language models with human
preferences in a variety of text generation tasks, including machine translation. For …

Generative Flow Networks (GFlowNets) have demonstrated significant performance
improvements for generating diverse discrete objects $ x $ given a reward function $ R (x) …