Related papers: Extrapolative Controlled Sequence Generation via I…
Conditional discrete generative models struggle to faithfully compose multiple input conditions. To address this, we derive a theoretically-grounded formulation for composing discrete probabilistic generative processes, with masked…
Expressive range analysis is a visualization-based technique used to evaluate the performance of generative models, particularly in game level generation. It typically employs two quantifiable metrics to position generated artifacts on a 2D…
We consider the problem of computing numerical invariants of programs, for instance bounds on the values of numerical program variables. More specifically, we study the problem of performing static analysis by abstract interpretation using…
The prediction of material properties plays a crucial role in the development and discovery of materials in diverse applications, such as batteries, semiconductors, catalysts, and pharmaceuticals. Recently, there has been a growing interest…
We aim to build image generation models that generalize to new domains from few examples. To this end, we first investigate the generalization properties of classic image generators, and discover that autoencoders generalize extremely well…
In E-commerce, a key challenge in text generation is to find a good trade-off between word diversity and accuracy (relevance) in order to make generated text appear more natural and human-like. In order to improve the relevance of generated…
Engineering new molecules with desirable functions and properties has the potential to extend our ability to engineer proteins beyond what nature has so far evolved. Advances in the so-called "de novo" design problem have recently been…
Controlled generation refers to the problem of creating text that contains stylistic or semantic attributes of interest. Many approaches reduce this problem to training a predictor of the desired attribute. For example, researchers hoping…
With the development of speech synthesis, recent research has focused on challenging tasks, such as speaker generation and emotion intensity control. Attribute interpolation is a common approach to these tasks. However, most previous…
Generative models reliant on sequential autoregression have been at the forefront of language generation for an extensive period, particularly following the introduction of widely acclaimed transformers. Despite its excellent performance,…
As the text generation capabilities of large language models become increasingly prominent, recent studies have focused on controlling particular aspects of the generated text to make it more personalized. However, most research on…
This paper deals with the solving of variational inequality problem where the constrained set is given as the intersection of a number of fixed-point sets. To this end, we present an extrapolated sequential constraint method. At each…
We present a Parallel Iterative Edit (PIE) model for the problem of local sequence transduction arising in tasks like Grammatical error correction (GEC). Recent approaches are based on the popular encoder-decoder (ED) model for sequence to…
The training of generative adversarial networks (GANs) is usually vulnerable to mode collapse and vanishing gradients. The evolutionary generative adversarial network (E-GAN) attempts to alleviate these issues by optimizing the learning…
This paper presents the Imputer, a neural sequence model that generates output sequences iteratively via imputations. The Imputer is an iterative generative model, requiring only a constant number of generation steps independent of the…
Time Series Generation (TSG) has emerged as a pivotal technique in synthesizing data that accurately mirrors real-world time series, becoming indispensable in numerous applications. Despite significant advancements in TSG, its efficacy…
We propose a simple and effective modeling framework for controlled generation of multiple, diverse outputs. We focus on the setting of generating the next sentence of a story given its context. As controllable dimensions, we consider…
Controllable text generation concerns two fundamental tasks of wide applications, namely generating text of given attributes (i.e., attribute-conditional generation), and minimally editing existing text to possess desired attributes (i.e.,…
Designing proteins with specific attributes offers an important solution to address biomedical challenges. Pre-trained protein large language models (LLMs) have shown promising results on protein sequence generation. However, to control…
The 21st century is presenting humankind with unprecedented environmental and medical challenges. The ability to design novel proteins tailored for specific purposes could transform our ability to respond timely to these issues. Recent…