Výsledky vyhledávání - "Rawls, Stephen"

Report

LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models

Autor: Veldanda, Akshaj Kumar, Zhang, Shi-Xiong, Das, Anirban, Chakraborty, Supriyo, Rawls, Stephen, Sahu, Sambit, Naphade, Milind

Large language models (LLMs) have revolutionized various domains, yet their utility comes with significant challenges related to outdated or problematic knowledge embedded during pretraining. This paper addresses the challenge of modifying LLMs to un

Externí odkaz: http://arxiv.org/abs/2409.13054

Zobrazit plný text záznamu

Report

Translation-Enhanced Multilingual Text-to-Image Generation

Autor: Li, Yaoyiran, Chang, Ching-Yun, Rawls, Stephen, Vulić, Ivan, Korhonen, Anna

Publikováno v: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023, pages 9174-9193

Research on text-to-image generation (TTI) still predominantly focuses on the English language due to the lack of annotated image-caption data in other languages; in the long run, this might widen inequitable access to TTI technology. In this work, w

Externí odkaz: http://arxiv.org/abs/2305.19216

Zobrazit plný text záznamu

Report

Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data

Autor: Lialin, Vladislav, Rawls, Stephen, Chan, David, Ghosh, Shalini, Rumshisky, Anna, Hamza, Wael

Publikováno v: 2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)

Scaling up weakly-supervised datasets has shown to be highly effective in the image-text domain and has contributed to most of the recent state-of-the-art computer vision and multimodal neural networks. However, existing large-scale video-text datase

Externí odkaz: http://arxiv.org/abs/2304.02080

Zobrazit plný text záznamu

Report

AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model

Autor: Soltan, Saleh, Ananthakrishnan, Shankar, FitzGerald, Jack, Gupta, Rahul, Hamza, Wael, Khan, Haidar, Peris, Charith, Rawls, Stephen, Rosenbaum, Andy, Rumshisky, Anna, Prakash, Chandana Satya, Sridhar, Mukund, Triefenbach, Fabian, Verma, Apurv, Tur, Gokhan, Natarajan, Prem

In this work, we demonstrate that multilingual large-scale sequence-to-sequence (seq2seq) models, pre-trained on a mixture of denoising and Causal Language Modeling (CLM) tasks, are more efficient few-shot learners than decoder-only models on various

Externí odkaz: http://arxiv.org/abs/2208.01448

Zobrazit plný text záznamu

Report

Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems

Publikováno v: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '22), August 14-18, 2022, Washington, DC, USA

We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the N

Externí odkaz: http://arxiv.org/abs/2206.07808

Zobrazit plný text záznamu

Report

Don't Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding

Autor: Zhu, Qile, Khan, Haidar, Soltan, Saleh, Rawls, Stephen, Hamza, Wael

Semantic parsing is one of the key components of natural language understanding systems. A successful parse transforms an input utterance to an action that is easily understood by the system. Many algorithms have been proposed to solve this problem,

Externí odkaz: http://arxiv.org/abs/2010.03714

Zobrazit plný text záznamu

Report

Implicit Language Model in LSTM for OCR

Autor: Sabir, Ekraam, Rawls, Stephen, Natarajan, Prem

Publikováno v: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 7 (2017) pp. 27-31

Neural networks have become the technique of choice for OCR, but many aspects of how and why they deliver superior performance are still unknown. One key difference between current neural network techniques using LSTMs and the previous state-of-the-a

Externí odkaz: http://arxiv.org/abs/1805.09441

Zobrazit plný text záznamu

Report

Learning Document Image Binarization from Data

Autor: Wu, Yue, Rawls, Stephen, AbdAlmageed, Wael, Natarajan, Premkumar

In this paper we present a fully trainable binarization solution for degraded document images. Unlike previous attempts that often used simple features with a series of pre- and post-processing, our solution encodes all heuristics about whether or no

Externí odkaz: http://arxiv.org/abs/1505.00529

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání