相关论文: Saying HelloWorld with QVTR-XSLT - A Solution to t…

We present our work on developing a multilingual, efficient text-to-text transformer that is suitable for handling long inputs. This model, called mLongT5, builds upon the architecture of LongT5, while leveraging the multilingual datasets…

This paper presents six document classification models using the latest transformer encoders and a high-performing ensemble model for a task of offensive language identification in social media. For the individual models, deep transformer…

Test-time scaling offers a promising way to improve the reasoning performance of vision-language large models (VLLMs) without additional training. In this paper, we explore a simple but effective approach for applying test-time scaling to…

The recent trend of using Large Language Models (LLMs) as tool agents in real-world applications underscores the necessity for comprehensive evaluations of their capabilities, particularly in complex scenarios involving planning, creating,…

This tutorial demonstrates workflows to incorporate text data into actuarial classification and regression tasks. The main focus is on methods employing transformer-based models. A dataset of car accident descriptions with an average length…

Inspired by the advancements in large language models based on transformers, we introduce the transformer quantum state (TQS): a versatile machine learning model for quantum many-body problems. In sharp contrast to Hamiltonian/task specific…

One of the most common ways to represent and share visual designs is with vector graphics. Designers working with vector graphics often explore layout alternatives and generate them by moving and resizing elements. The motivation for this…

This paper proposes a simple, yet effective framework, called GiT, simultaneously applicable for various vision tasks only with a vanilla ViT. Motivated by the universality of the Multi-layer Transformer architecture (e.g, GPT) widely used…

The application of quantum machine learning to large-scale high-resolution image datasets is not yet possible due to the limited number of qubits and relatively high level of noise in the current generation of quantum devices. In this work,…

Recent advancements in Long Chain-of-Thought (CoT) reasoning models have improved performance on complex tasks, but they suffer from overthinking, which generates redundant reasoning steps, especially for simple questions. This paper…

The evaluation of Handwritten Text Recognition (HTR) models during their development is straightforward: because HTR is a supervised problem, the usual data split into training, validation, and test data sets allows the evaluation of models…

Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning (ICL), where models adapt to new tasks through example-based prompts without requiring parameter updates. However, understanding how tasks are…

This paper describes our participation in SemEval-2023 Task 10, whose goal is the detection of sexism in social media. We explore some of the most popular transformer models such as BERT, DistilBERT, RoBERTa, and XLNet. We also study…

Large language models (LLMs) have demonstrated strong capabilities in using external tools to address user inquiries. However, most existing evaluations assume tool use in short contexts, offering limited insight into model behavior during…

The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or…

This paper describes our work in participation of the IWSLT-2021 offline speech translation task. Our system was built in a cascade form, including a speaker diarization module, an Automatic Speech Recognition (ASR) module and a Machine…

Large language models (LLMs) demonstrate impressive multilingual capability, but their performance varies substantially across different languages. In this work, we introduce a simple yet effective method, called cross-lingual-thought…

This paper presents our work for the ninth edition of the Dialogue System Technology Challenge (DSTC9). Our solution addresses the track number four: Simulated Interactive MultiModal Conversations. The task consists in providing an…

Machine translation between many languages at once is highly challenging, since training with ground truth requires supervision between all language pairs, which is difficult to obtain. Our key insight is that, while languages may vary…

We present ControlLLM, a novel framework that enables large language models (LLMs) to utilize multi-modal tools for solving complex real-world tasks. Despite the remarkable performance of LLMs, they still struggle with tool invocation due…