相关论文: The NYU-CUBoulder Systems for SIGMORPHON 2020 Task…

This paper presents our submission to Task 2 of the Workshop on Noisy User-generated Text. We explore improving the performance of a pre-trained transformer-based language model fine-tuned for text classification through an ensemble…

We propose a holistic approach for deploying Small Language Models (SLMs) as function-calling agents within vehicles as edge devices, offering a more flexible and robust alternative to traditional rule-based systems. By leveraging SLMs, we…

Large Language Models (LLMs) have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal…

Generative machine learning models have revolutionized material discovery by capturing complex structure-property relationships, yet extending these approaches to the inverse design of three-dimensional metamaterials remains limited by…

In-context learning (ICL) has revolutionized the capabilities of transformer models in NLP. In our project, we extend the understanding of the mechanisms underpinning ICL by exploring whether transformers can learn from sequential,…

This paper presents the MasonTigers entry to the SemEval-2024 Task 8 - Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection. The task encompasses Binary Human-Written vs. Machine-Generated Text…

The unusual properties of in-context learning (ICL) have prompted investigations into the internal mechanisms of large language models. Prior work typically focuses on either special attention heads or task vectors at specific layers, but…

The development of the transformer-based text-to-image models are impeded by its slow generation and complexity for high-resolution images. In this work, we put forward a solution based on hierarchical transformers and local parallel…

To capture user preference, transformer models have been widely applied to model sequential user behavior data. The core of transformer architecture lies in the self-attention mechanism, which computes the pairwise attention scores in a…

We study the joint learning of image-to-text and text-to-image generations, which are naturally bi-directional tasks. Typical existing works design two separate task-specific models for each task, which impose expensive design efforts. In…

With the rising popularity of Transformer-based large language models (LLMs), reducing their high inference costs has become a significant research focus. One effective approach is to compress the long input contexts. Existing methods…

Partially Supervised Multi-Task Learning (PS-MTL) aims to leverage knowledge across tasks when annotations are incomplete. Existing approaches, however, have largely focused on the simpler setting of homogeneous, dense prediction tasks,…

Transformer based knowledge tracing model is an extensively studied problem in the field of computer-aided education. By integrating temporal features into the encoder-decoder structure, transformers can processes the exercise information…

Recently, large language models (LLMs) enhanced by self-reflection have achieved promising performance on machine translation. The key idea is guiding LLMs to generate translation with human-like feedback. However, existing self-reflection…

In this work, we aim to compress the vision tokens of a Large Vision Language Model (LVLM) into a representation that is simultaneously suitable for (a) generative and (b) discriminative tasks, (c) is nearly lossless, and (d) is…

Modern large language models (LLMs) employ diverse logical inference mechanisms for reasoning, making the strategic optimization of these approaches critical for advancing their capabilities. This paper systematically investigate the…

We make significant progress toward the classification of 2nd order superintegrable systems on 3-dimensional conformally flat space that have functionally linearly dependent (FLD) symmetry generators, with special emphasis on complex…

For our contribution to the Blizzard Challenge 2023, we improved on the system we submitted to the Blizzard Challenge 2021. Our approach entails a rule-based text-to-phoneme processing system that includes rule-based disambiguation of…

Human translators routinely have to translate rare inflections of words - due to the Zipfian distribution of words in a language. When translating from Spanish, a good translator would have no problem identifying the proper translation of a…

Transformers have emerged as a powerful tool for a broad range of natural language processing tasks. A key component that drives the impressive performance of Transformers is the self-attention mechanism that encodes the influence or…