Text Generation aims to produce plausible and readable text in human language from input
data. The resurgence of deep learning has greatly advanced this field, in particular, with the …

After more than 70 years of evolution, great achievements have been made in machine
translation. Especially in recent years, translation quality has been greatly improved with the …

Controlling the behavior of language models (LMs) without re-training is a major open
problem in natural language generation. While recent works have demonstrated successes …

Generative transformers have experienced rapid popularity growth in the computer vision
community in synthesizing high-fidelity and high-resolution images. The best generative …

Recently, diffusion models have emerged as a new paradigm for generative models.
Despite the success in domains using continuous signals such as vision and audio …

Transformers have been recently adapted for large scale image classification, achieving
high scores shaking up the long supremacy of convolutional neural networks. However the …

Abstract Neural network-based Combinatorial Optimization (CO) methods have shown
promising results in solving various NP-complete (NPC) problems without relying on hand …

We present a new method that views object detection as a direct set prediction problem. Our
approach streamlines the detection pipeline, effectively removing the need for many hand …

Algorithmic reasoning requires capabilities which are most naturally understood through
recurrent models of computation, like the Turing machine. However, Transformer models …

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading
performances in many generative tasks. However, the inherited iterative sampling process …