相关论文: Alleviating Sequence Information Loss with Data Ov…

The Age-of-Information (AoI) is a new performance metric recently proposed for measuring the freshness of information in information-update systems. In this work, we conduct a systematic and comparative study to investigate the impact of…

Sentence Split and Rephrase aims to break down a complex sentence into several simple sentences with its meaning preserved. Previous studies tend to address the issue by seq2seq learning from parallel sentence pairs, which takes a complex…

With the expansion of data availability, machine learning (ML) has achieved remarkable breakthroughs in both academia and industry. However, imbalanced data distributions are prevalent in various types of raw data and severely hinder the…

Modern reasoning models, such as OpenAI's o1 and DeepSeek-R1, exhibit impressive problem-solving capabilities but suffer from critical inefficiencies: high inference latency, excessive computational resource consumption, and a tendency…

Class imbalance (CI) in classification problems arises when the number of observations belonging to one class is lower than the other. Ensemble learning combines multiple models to obtain a robust model and has been prominently used with…

In this paper, we analyze the impact of different encoding schemes on the age of information (AoI) performance in a point-to-point system, where a source generates packets based on the status updates collected from multiple sensors and…

As an emerging metric for the timeliness of information delivery, Age-of-Information (AoI) raises a special interest in the research area of tolerance-critical communications, wherein sufficiently short blocklength is usually adopted as an…

A multilingual tokenizer is a fundamental component of multilingual neural machine translation. It is trained from a multilingual corpus. Since a skewed data distribution is considered to be harmful, a sampling strategy is usually used to…

As part of autonomous car driving systems, semantic segmentation is an essential component to obtain a full understanding of the car's environment. One difficulty, that occurs while training neural networks for this purpose, is class…

Large Language Models (LLMs) have excelled in various tasks but perform better in high-resource scenarios, which presents challenges in low-resource scenarios. Data scarcity and the inherent difficulty of adapting LLMs to specific tasks…

Subword tokenization is a key part of many NLP pipelines. However, little is known about why some tokenizer and hyperparameter combinations lead to better downstream model performance than others. We propose that good tokenizers lead to…

Age of Information (AoI), measures the time elapsed since the last received information packet was generated at the source. We consider the problem of AoI minimization for single-hop flows in a wireless network, under pairwise interference…

Standard Byte-Pair Encoding (BPE) tokenization compresses text by pairing a learned token vocabulary with a detailed merge list. Recent work has shown that this merge list exposes a potential attack surface for extracting information about…

Compression of integer sets and sequences has been extensively studied for settings where elements follow a uniform probability distribution. In addition, methods exist that exploit clustering of elements in order to achieve higher…

Motivated by DNA-based data storage, we investigate a system where digital information is stored in an unordered set of several vectors over a finite alphabet. Each vector begins with a unique index that represents its position in the whole…

Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimized long-sequence inference through operators, model…

Large language models encode impressively broad world knowledge in their parameters. However, the knowledge in static language models falls out of date, limiting the model's effective "shelf life." While online fine-tuning can reduce this…

Data imbalance, that is the disproportion between the number of training observations coming from different classes, remains one of the most significant challenges affecting contemporary machine learning. The negative impact of data…

Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly stemming from communication bottlenecks in attention…

Sequence modeling has important applications in natural language processing and computer vision. Recently, the transformer-based models have shown strong performance on various sequence modeling tasks, which rely on attention to capture…