Related papers: Efficient Generation of Low Autocorrelation Binary…

In this paper, we develop a new cellular automata-based linear model for several nonlinear pseudorandom number generators with practical applications in symmetric cryptography. Such a model generates all the solutions of linear binary…

Sensational headlines are headlines that capture people's attention and generate reader interest. Conventional abstractive headline generation methods, unlike human writers, do not optimize for maximal reader attention. In this paper, we…

This work presents SimpleAR, a vanilla autoregressive visual generation framework without complex architecure modifications. Through careful exploration of training and inference optimization, we demonstrate that: 1) with only 0.5B…

We consider the problem of making a quick decision in favor of one of two possible physical signal models while the numerical measurements are acquired by sensing devices featuring minimal digitization complexity. Therefore, the digital…

This paper performs the analysis necessary to bound the running time of known, efficient algorithms for generating all longest common subsequences. That is, we bound the running time as a function of input size for algorithms with time…

Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio. They pose density estimation as a sequence modeling task, where a recurrent neural…

Large language models (LLMs) show strong potential for neural architecture generation, yet existing approaches produce complete model implementations from scratch -- computationally expensive and yielding verbose code. We propose Delta-Code…

The difficulty of generating coherent long texts lies in the fact that existing models overwhelmingly focus on predicting local words, and cannot make high level plans on what to generate or capture the high-level discourse dependencies…

In this paper, we use large language models to generate personalized stories for language learners, using only the vocabulary they know. The generated texts are specifically written to teach the user new vocabulary by simply reading stories…

Weighted Hamming distance, as a similarity measure between binary codes and binary queries, provides superior accuracy in search tasks than Hamming distance. However, how to efficiently and accurately find $K$ binary codes that have the…

Large language models (LLMs) have achieved remarkable progress in natural language processing, but their high computational and memory costs hinder deployment on resource-constrained devices. Binarization represents the most extreme form of…

Structured texts refer to texts containing structured elements beyond plain texts, such as code snippets and placeholders. Such structured texts increasingly require segmentation into semantically meaningful components, which cannot be…

We present a general framework for training spiking neural networks (SNNs) to perform binary classification on multivariate time series, with a focus on step-wise prediction and high precision at low false alarm rates. The approach uses the…

The popularity of bi-level optimization (BO) in deep learning has spurred a growing interest in studying gradient-based BO algorithms. However, existing algorithms involve two coupled learning rates that can be affected by approximation…

Extending the context length (i.e., the maximum supported sequence length) of LLMs is of paramount significance. To facilitate long context training of LLMs, sequence parallelism has emerged as an essential technique, which scatters each…

We analyze the signum-generation method for creating random dichotomic sequences with prescribed correlation properties. The method is based on a binary mapping of the convolution of continuous random numbers with some function originated…

This paper shows how to train binary networks to within a few percent points ($\sim 3-5 \%$) of the full precision counterpart. We first show how to build a strong baseline, which already achieves state-of-the-art accuracy, by combining…

In neural text generation such as neural machine translation, summarization, and image captioning, beam search is widely used to improve the output text quality. However, in the neural generation setting, hypotheses can finish in different…

Several methods for generating random Steiner triple systems (STSs) have been proposed in the literature, such as Stinson's hill-climbing algorithm and Cameron's algorithm, but these are not yet completely understood. Those algorithms, as…

Recent neural headline generation models have shown great results, but are generally trained on very large datasets. We focus our efforts on improving headline quality on smaller datasets by the means of pretraining. We propose new methods…