Search Results for author: Junyu Lu

Found 18 papers, 4 papers with code

Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support

no code implementations26 Jan 2024 XiaoJun Wu, Dixiang Zhang, Ruyi Gan, Junyu Lu, Ziwei Wu, Renliang Sun, Jiaxing Zhang, Pingjian Zhang, Yan Song

Recent advancements in text-to-image models have significantly enhanced image generation capabilities, yet a notable gap of open-source models persists in bilingual or Chinese language support.

Language Modelling Text-to-Image Generation

Unlocking the Potential of Large Language Models for Explainable Recommendations

1 code implementation25 Dec 2023 Yucong Luo, Mingyue Cheng, Hao Zhang, Junyu Lu, Qi Liu, Enhong Chen

In this study, we propose LLMXRec, a simple yet effective two-stage explainable recommendation framework aimed at further boosting the explanation quality by employing LLMs.

Decision Making Explainable Recommendation +2

Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects

no code implementations8 Dec 2023 Junyu Lu, Ruyi Gan, Dixiang Zhang, XiaoJun Wu, Ziwei Wu, Renliang Sun, Jiaxing Zhang, Pingjian Zhang, Yan Song

During the instruction fine-tuning stage, we introduce semantic-aware visual feature extraction, a crucial method that enables the model to extract informative features from concrete visual objects.

Image Captioning object-detection +5

iDesigner: A High-Resolution and Complex-Prompt Following Text-to-Image Diffusion Model for Interior Design

no code implementations7 Dec 2023 Ruyi Gan, XiaoJun Wu, Junyu Lu, Yuanhe Tian, Dixiang Zhang, Ziwei Wu, Renliang Sun, Chang Liu, Jiaxing Zhang, Pingjian Zhang, Yan Song

However, there are few specialized models in certain domains, such as interior design, which is attributed to the complex textual descriptions and detailed visual elements inherent in design, alongside the necessity for adaptable resolution.

Image Generation

Ziya2: Data-centric Learning is All LLMs Need

no code implementations6 Nov 2023 Ruyi Gan, Ziwei Wu, Renliang Sun, Junyu Lu, XiaoJun Wu, Dixiang Zhang, Kunhao Pan, Ping Yang, Qi Yang, Jiaxing Zhang, Yan Song

Although many such issues are addressed along the line of research on LLMs, an important yet practical limitation is that many studies overly pursue enlarging model sizes without comprehensively analyzing and optimizing the use of pre-training data in their learning process, as well as appropriate organization and leveraging of such data in training LLMs under cost-effective settings.

Ziya-Visual: Bilingual Large Vision-Language Model via Multi-Task Instruction Tuning

no code implementations12 Oct 2023 Junyu Lu, Dixiang Zhang, XiaoJun Wu, Xinyu Gao, Ruyi Gan, Jiaxing Zhang, Yan Song, Pingjian Zhang

Recent advancements enlarge the capabilities of large language models (LLMs) in zero-shot image-to-text generation and understanding by integrating multi-modal inputs.

Image Captioning In-Context Learning +5

Hate Speech Detection via Dual Contrastive Learning

no code implementations10 Jul 2023 Junyu Lu, Hongfei Lin, Xiaokun Zhang, Zhaoqing Li, Tongyue Zhang, Linlin Zong, Fenglong Ma, Bo Xu

Our framework jointly optimizes the self-supervised and the supervised contrastive learning loss for capturing span-level information beyond the token-level emotional semantics used in existing models, particularly detecting speech containing abusive and insulting words.

Contrastive Learning Hate Speech Detection

UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective

no code implementations17 May 2023 Ping Yang, Junyu Lu, Ruyi Gan, Junjie Wang, Yuxiang Zhang, Jiaxing Zhang, Pingjian Zhang

We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment analysis.

Event Extraction named-entity-recognition +3

Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks

1 code implementation8 May 2023 Junyu Lu, Bo Xu, Xiaokun Zhang, Changrong Min, Liang Yang, Hongfei Lin

In addition, it is crucial to introduce lexical knowledge to detect the toxicity of posts, which has been a challenge for researchers.

Hate Speech Detection

Flat Multi-modal Interaction Transformer for Named Entity Recognition

no code implementations COLING 2022 Junyu Lu, Dixiang Zhang, Pingjian Zhang

Then, we transform the fine-grained semantic representation of the vision and text into a unified lattice structure and design a novel relative position encoding to match different modalities in Transformer.

Boundary Detection Multi-modal Named Entity Recognition +2

Unified BERT for Few-shot Natural Language Understanding

no code implementations24 Jun 2022 Junyu Lu, Ping Yang, Ruyi Gan, Jing Yang, Jiaxing Zhang

Even as pre-trained language models share a semantic encoder, natural language understanding suffers from a diversity of output schemas.

Natural Language Understanding

SiNER: A Large Dataset for Sindhi Named Entity Recognition

no code implementations LREC 2020 Wazir Ali, Junyu Lu, Zenglin Xu

We introduce the SiNER: a named entity recognition (NER) dataset for low-resourced Sindhi language with quality baselines.

named-entity-recognition Named Entity Recognition +1

Word Embedding based New Corpus for Low-resourced Language: Sindhi

no code implementations28 Nov 2019 Wazir Ali, Jay Kumar, Junyu Lu, Zenglin Xu

Our intrinsic evaluation results demonstrate the high quality of our generated Sindhi word embeddings using SG, CBoW, and GloVe as compare to SdfastText word representations.

Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.