no code implementations • 11 Apr 2024 • Samuel Cahyawijaya, Delong Chen, Yejin Bang, Leila Khalatbari, Bryan Wilie, Ziwei Ji, Etsuko Ishii, Pascale Fung
there is an urgent need to understand the scope and nature of human values injected into these models before their release.
no code implementations • 27 Mar 2024 • Yejin Bang, Delong Chen, Nayeon Lee, Pascale Fung
We propose to measure political bias in LLMs by analyzing both the content and style of their generated content regarding political issues.
1 code implementation • 22 Feb 2024 • Delong Chen, Samuel Cahyawijaya, Jianfeng Liu, Baoyuan Wang, Pascale Fung
Transformer-based vision models typically tokenize images into fixed-size square patches as input units, which lacks the adaptability to image content and overlooks the inherent pixel grouping structure.
no code implementations • 3 Jan 2024 • Fan Liu, Tianshu Zhang, Wenwen Dai, Wenwen Cai, Xiaocong Zhou, Delong Chen
Therefore, in this survey, we introduce and analyze the research advancements in few-shot adaptation methods for multi-modal models, summarizing commonly used datasets and experimental setups, and comparing the results of different methods.
1 code implementation • 20 Sep 2023 • Xinyu Zhou, Delong Chen, Yudong Chen
This paper explores the potential of constructing an AI spoken dialogue system that "thinks how to respond" and "thinks how to speak" simultaneously, which more closely aligns with the human speech production process compared to the current cascade pipeline of independent chatbot and Text-to-Speech (TTS) modules.
2 code implementations • 3 Jul 2023 • Delong Chen, Jianfeng Liu, Wenliang Dai, Baoyuan Wang
This side effect negatively impacts the model's ability to format responses appropriately -- for instance, its "politeness" -- due to the overly succinct and unformatted nature of raw annotations, resulting in reduced human preference.
1 code implementation • 19 Jun 2023 • Fan Liu, Delong Chen, Zhangqingyun Guan, Xiaocong Zhou, Jiale Zhu, Qiaolin Ye, Liyong Fu, Jun Zhou
However, these models primarily learn low-level features and require annotated data for fine-tuning.
Ranked #2 on Cross-Modal Retrieval on RSITMD (using extra training data)
1 code implementation • 15 Jun 2023 • Zhuoran Zhao, Jinbin Bai, Delong Chen, Debang Wang, Yubo Pan
Generating the motion of orchestral conductors from a given piece of symphony music is a challenging task since it requires a model to learn semantic music features and capture the underlying distribution of real conducting motion.
no code implementations • 30 Apr 2023 • Sai Yang, Fan Liu, Delong Chen, Jun Zhou
To address this need, we prove theoretically that leveraging ensemble learning on the base classes can correspondingly reduce the true error in the novel classes.
1 code implementation • 22 Jun 2022 • Delong Chen, Zhao Wu, Fan Liu, Zaiquan Yang, Huaxi Huang, Ying Tan, Erjin Zhou
Based on this understanding, in this paper, Prototypical Contrastive Language Image Pretraining (ProtoCLIP) is introduced to enhance such grouping by boosting its efficiency and increasing its robustness against the modality gap.
1 code implementation • 16 Jun 2022 • Delong Chen, Ruizhi Zhou, Yanling Pan, Fan Liu
Specifically, training of FloodDAN includes two stages: in the first stage, we train a rainfall encoder and a prediction head to learn general transferable hydrological knowledge on large-scale source domain data; in the second stage, we transfer the knowledge in the pretrained encoder into the rainfall encoder of target domain through adversarial domain alignment.
1 code implementation • Journal of Computer Science and Technology 2022 • Fan Liu, Delong Chen, Ruizhi Zhou, Sai Yang, Feng Xu
Therefore, we propose a novel Music Motion Synchronized Generative Adversarial Network (M2S-GAN), which generates motions according to the automatically learned music representations.
no code implementations • 8 Feb 2022 • Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Yejin Bang, Delong Chen, Ho Shu Chan, Wenliang Dai, Andrea Madotto, Pascale Fung
This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation and data-to-text generation.
2 code implementations • 28 Jul 2021 • Delong Chen, Fan Liu, Zewen Li, Feng Xu
In this demo, we present VirtualConductor, a system that can generate conducting video from any given music and a single user's image.
1 code implementation • 20 Jul 2021 • Delong Chen, Fan Liu, Zheqi Zhang, Xiaomin Lu, Zewen Li
Several parallel graph neural networks are separately trained on wavelet decomposed data, and the reconstruction of each model's prediction forms the final SWH prediction.
no code implementations • 9 Jun 2020 • Fan Liu, Delong Chen, Fei Wang, Zewen Li, Feng Xu
Face recognition under this situation is referred to as single sample face recognition and poses significant challenges to the effective training of deep models.
no code implementations • 9 Jun 2020 • Delong Chen, Shunhui Ji, Fan Liu, Zewen Li, Xinyu Zhou
The pandemic of COVID-19 has caused millions of infections, which has led to a great loss all over the world, socially and economically.