The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by
its unnormalized (log-) probabilities. Over the past years, the machine learning community …

Three billion years of evolution has produced a tremendous diversity of protein molecules,
but the full potential of proteins is likely to be much greater. Accessing this potential has …

Selecting a suitable pretraining dataset is crucial for both general-domain (eg, GPT-3) and
domain-specific (eg, Codex) language models (LMs). We formalize this problem as selecting …

The field of graph neural networks (GNNs) has seen rapid and incredible strides over the
recent years. Graph neural networks, also known as deep learning on graphs, graph …

Text generation is of great importance to many natural language processing applications.
However, maximization-based decoding methods (eg, beam search) of neural language …

Generative flows and diffusion models have been predominantly trained on ordinal data, for
example natural images. This paper introduces two extensions of flows and diffusion for …

Abstract To build Video Question Answering (VideoQA) systems capable of assisting
humans in daily activities, seeking answers from long-form videos with diverse and complex …

We present a novel semi-supervised semantic segmentation method which jointly achieves
two desiderata of segmentation model regularities: the label-space consistency property …

Semi-supervised learning lately has shown much promise in improving deep learning
models when labeled data is scarce. Common among recent approaches is the use of …

Breaking down a problem into intermediate steps has demonstrated impressive
performance in Large Language Model (LLM) reasoning. However, the growth of the …