中文
相关论文

相关论文: GENIUS: Sketch-based Language Model Pre-training v…

200 篇论文

With the advances of deep learning techniques, text generation is attracting increasing interest in the artificial intelligence (AI) community, because of its wide applications and because it is an essential component of AI. Traditional…

计算与语言 · 计算机科学 2023-09-19 Lili Mou

Despite the superior performance of large language models to generate natural language texts, it is hard to generate texts with correct logic according to a given task, due to the difficulties for neural models to capture implied rules from…

计算与语言 · 计算机科学 2024-07-08 Fan Zhang , Kebing Jin , Hankz Hankui Zhuo

The scarcity of free-hand sketch presents a challenging problem. Despite the emergence of some large-scale sketch datasets, these datasets primarily consist of sketches at the single-object level. There continues to be a lack of large-scale…

计算机视觉与模式识别 · 计算机科学 2024-05-30 Zhenbei Wu , Qiang Wang , Jie Yang

Neural natural language generation (NLG) and understanding (NLU) models are data-hungry and require massive amounts of annotated data to be competitive. Recent frameworks address this bottleneck with generative models that synthesize weak…

计算与语言 · 计算机科学 2021-02-09 Ernie Chang , Vera Demberg , Alex Marin

Instruction-tuned large language models have shown remarkable performance in aligning generated text with user intentions across various tasks. However, maintaining human-like discourse structure in the generated text remains a challenging…

计算与语言 · 计算机科学 2023-12-20 Yinhong Liu , Yixuan Su , Ehsan Shareghi , Nigel Collier

Recent advances in Generative Artificial Intelligence (GenAI) have transformed educational content creation, particularly in developing tutor training materials. However, biases embedded in AI-generated content--such as gender, racial, or…

计算与语言 · 计算机科学 2025-05-20 Jingyang Peng , Wenyuan Shen , Jiarui Rao , Jionghao Lin

Can a user create a deep generative model by sketching a single example? Traditionally, creating a GAN model has required the collection of a large-scale dataset of exemplars and specialized knowledge in deep learning. In contrast,…

计算机视觉与模式识别 · 计算机科学 2021-09-21 Sheng-Yu Wang , David Bau , Jun-Yan Zhu

Recent remarkable improvements in large-scale text-to-image generative models have shown promising results in generating high-fidelity images. To further enhance editability and enable fine-grained generation, we introduce a…

计算机视觉与模式识别 · 计算机科学 2023-04-20 Kangyeol Kim , Sunghyun Park , Junsoo Lee , Jaegul Choo

Large language models (LLMs) have demonstrated immense potential across various tasks. However, research for exploring and improving the capabilities of LLMs in interpreting graph structures remains limited. To address this gap, we conduct…

计算与语言 · 计算机科学 2025-02-17 Jie He , Yijun Yang , Wanqiu Long , Deyi Xiong , Victor Gutierrez-Basulto , Jeff Z. Pan

With the involvement of artificial intelligence (AI), sketches can be automatically generated under certain topics. Even though breakthroughs have been made in previous studies in this area, a relatively high proportion of the generated…

计算机视觉与模式识别 · 计算机科学 2020-11-10 Yunkui Pang , Zhiqing Pan , Ruiyang Sun , Shuchong Wang

A large number of annotated training images is crucial for training successful scene text recognition models. However, collecting sufficient datasets can be a labor-intensive and costly process, particularly for low-resource languages. To…

计算机视觉与模式识别 · 计算机科学 2023-06-28 Yangchen Xie , Xinyuan Chen , Hongjian Zhan , Palaiahankote Shivakum , Bing Yin , Cong Liu , Yue Lu

Scene graph generation (SGG) is a sophisticated task that suffers from both complex visual features and dataset long-tail problem. Recently, various unbiased strategies have been proposed by designing novel loss functions and data balancing…

计算机视觉与模式识别 · 计算机科学 2023-03-03 Xiaoguang Chang , Teng Wang , Shaowei Cai , Changyin Sun

Automatic question generation is an important technique that can improve the training of question answering, help chatbots to start or continue a conversation with humans, and provide assessment materials for educational purposes. Existing…

计算与语言 · 计算机科学 2019-02-28 Bang Liu , Mingjun Zhao , Di Niu , Kunfeng Lai , Yancheng He , Haojie Wei , Yu Xu

The recent surge of generative AI has been fueled by the generative power of diffusion probabilistic models and the scalable capabilities of large language models. Despite their potential, it remains elusive whether diffusion language…

计算与语言 · 计算机科学 2025-02-25 Jiasheng Ye , Zaixiang Zheng , Yu Bao , Lihua Qian , Quanquan Gu

In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements. Existing language generation techniques are usually based on recurrent…

计算与语言 · 计算机科学 2019-02-05 Ning Miao , Hao Zhou , Lili Mou , Rui Yan , Lei Li

Many natural language processing applications use language models to generate text. These models are typically trained to predict the next word in a sequence, given the previous words and some context such as an image. However, at test time…

机器学习 · 计算机科学 2016-05-10 Marc'Aurelio Ranzato , Sumit Chopra , Michael Auli , Wojciech Zaremba

Generative AI presents transformative potential across various domains, from creative arts to scientific visualization. However, the utility of AI-generated imagery is often compromised by visual flaws, including anatomical inaccuracies,…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Zhenyu Yu , Chee Seng Chan

Generalization to unseen real-world scenarios for robot manipulation requires exposure to diverse datasets during training. However, collecting large real-world datasets is intractable due to high operational costs. For robot learning to…

机器人学 · 计算机科学 2024-09-04 Zoey Chen , Zhao Mandi , Homanga Bharadhwaj , Mohit Sharma , Shuran Song , Abhishek Gupta , Vikash Kumar

We introduce the Curious About Uncertain Scene (CAUS) dataset, designed to enable Large Language Models, specifically GPT-4, to emulate human cognitive processes for resolving uncertainties. Leveraging this dataset, we investigate the…

人工智能 · 计算机科学 2024-05-21 Minjung Shin , Donghyun Kim , Jeh-Kwang Ryu

Large language models have made revolutionary progress in generating human-like text, yet their outputs often tend to be generic, exhibiting insufficient structural diversity, which limits personalized expression. Recent advances in…

计算与语言 · 计算机科学 2025-10-02 Ruqian Zhang , Yijiao Zhang , Juan Shen , Zhongyi Zhu , Annie Qu