Related papers: Efficient Generation of Low Autocorrelation Binary…
We present RLSS: a reinforcement learning algorithm for sequential scene generation. This is based on employing the proximal policy optimization (PPO) algorithm for generative problems. In particular, we consider how to effectively reduce…
J. Y. Hyun, et al. (Des. Codes Cryptogr., vol. 88, pp. 2475-2492, 2020) constructed some optimal and minimal binary linear codes generated by one or two order ideals in hierarchical posets of two levels. At the end of their paper, they left…
Video prediction has been an active topic of research in the past few years. Many algorithms focus on pixel-level predictions, which generates results that blur and disintegrate within a few frames. In this project, we use a hierarchical…
Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent…
Support vector machines (SVM) and other kernel techniques represent a family of powerful statistical classification methods with high accuracy and broad applicability. Because they use all or a significant portion of the training data,…
Sequences with good randomness properties are quite important for stream ciphers. In this paper, a new class of quaternary sequences is constructed by using generalized cyclotomic classes of $\mathbb{Z}_{2p^m}$ $(m\geq1)$. The exact values…
Large Language Models (LLMs) have been shown to be capable of performing high-level planning for long-horizon robotics tasks, yet existing methods require access to a pre-defined skill library (e.g. picking, placing, pulling, pushing,…
Assuming iterative decoding for binary erasure channels (BECs), a novel tree-based technique for upper bounding the bit error rates (BERs) of arbitrary, finite low-density parity-check (LDPC) codes is provided and the resulting bound can be…
Computing high-quality independent sets quickly is an important problem in combinatorial optimization. Several recent algorithms have shown that kernelization techniques can be used to find exact maximum independent sets in medium-sized…
In this paper we propose a problem-driven scenario generation approach to the single-period portfolio selection problem which use tail risk measures such as conditional value-at-risk. Tail risk measures are useful for quantifying potential…
It is desirable but challenging to generate content-rich long videos in the scale of minutes. Autoregressive large language models (LLMs) have achieved great success in generating coherent and long sequences of tokens in the domain of…
The linear complexity of a sequence $s$ is one of the measures of its predictability. It represents the smallest degree of a linear recursion which the sequence satisfies. There are several algorithms to find the linear complexity of a…
The prevalence of Large Language Models (LLMs) for generating multilingual text and source code has only increased the imperative for machine-generated content detectors to be accurate and efficient across domains. Current detectors,…
Fine-tuning on task-specific data to boost downstream performance is a crucial step for leveraging Large Language Models (LLMs). However, previous studies have demonstrated that fine-tuning the models on several adversarial samples or even…
We propose a hierarchical approach for making long-term predictions of future frames. To avoid inherent compounding errors in recursive pixel-level prediction, we propose to first estimate high-level structure in the input frames, then…
This paper describes experiments on fine-tuning a small language model to generate forecasts of long-horizon stock price movements. Inputs to the model are narrative text from 10-K reports of large market capitalization companies in the S&P…
High-utility sequential pattern mining is an emerging topic in the field of Knowledge Discovery in Databases. It consists of discovering subsequences having a high utility (importance) in sequences, referred to as high-utility sequential…
Neural text generation is a key tool in natural language applications, but it is well known there are major problems at its core. In particular, standard likelihood training and decoding leads to dull and repetitive outputs. While some…
The advent of "next-generation" DNA sequencing (NGS) technologies has meant that collections of hundreds of millions of DNA sequences are now commonplace in bioinformatics. Knowing the longest common prefix array (LCP) of such a collection…
Cross-lingual summarization (CLS) aims to generate a summary for the source text in a different target language. Currently, instruction-tuned large language models (LLMs) excel at various English tasks. However, unlike languages such as…