115 citations · 613 across the 46 of their papers we have counts for
46 papers
BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization
Chaoya Jiang, Haiyang Xu, Wei Ye +7
Vision Transformer (ViT) based Vision-Language Pre-training (VLP) models have demonstrated impressive performance in various tasks. However, the lengthy visual token sequences fed…
DiffDTM: A conditional structure-free framework for bioactive molecules generation targeted for dual proteins
Lei Huang, Zheng Yuan, Huihui Yan +9
Advances in deep generative models shed light on de novo molecule generation with desired properties. However, molecule generation targeted for dual protein targets still faces for…
Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning
Zhen-Ru Zhang, Chuanqi Tan, Haiyang Xu +3
Fine-tuning large pre-trained language models on various downstream tasks with whole parameters is prohibitively expensive. Hence, Parameter-efficient fine-tuning has attracted att…
VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning
Zhen-Ru Zhang, Chuanqi Tan, Songfang Huang +1
Recent studies have demonstrated the potential of cross-lingual transferability by training a unified Transformer encoder for multiple languages. In addition to involving the maske…
RRHF: Rank Responses to Align Language Models with Human Feedback without tears
Zheng Yuan, Hongyi Yuan, Chuanqi Tan +3
Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models with human preferences, significantly enhancing the quality of interactions bet…
Revisiting Automatic Question Summarization Evaluation in the Biomedical Domain
Hongyi Yuan, Yaoyun Zhang, Fei Huang +1
Automatic evaluation metrics have been facilitating the rapid development of automatic summarization methods by providing instant and fair assessments of the quality of summaries.…
How well do Large Language Models perform in Arithmetic tasks?
Zheng Yuan, Hongyi Yuan, Chuanqi Tan +2
Large language models have emerged abilities including chain-of-thought to answer math word problems step by step. Solving math word problems not only requires abilities to disasse…
RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training
Zheng Yuan, Qiao Jin, Chuanqi Tan +4
Vision-and-language multi-modal pretraining and fine-tuning have shown great success in visual question answering (VQA). Compared to general domain VQA, the performance of biomedic…
Molecular Geometry-aware Transformer for accurate 3D Atomic System modeling
Zheng Yuan, Yaoyun Zhang, Chuanqi Tan +3
Molecular dynamic simulations are important in computational physics, chemistry, material, and biology. Machine learning-based methods have shown strong abilities in predicting mol…
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
Haiyang Xu, Qinghao Ye, Ming Yan +12
Recent years have witnessed a big convergence of language, vision, and multi-modal pretraining. In this work, we present mPLUG-2, a new unified paradigm with modularized design for…
Learning Trajectory-Word Alignments for Video-Language Tasks
Xu Yang, Zhangzikang Li, Haiyang Xu +7
In a video, an object usually appears as the trajectory, i.e., it spans over a few spatial but longer temporal patches, that contains abundant spatiotemporal contexts. However, mod…
SeqDiffuSeq: Text Diffusion with Encoder-Decoder Transformers
Hongyi Yuan, Zheng Yuan, Chuanqi Tan +2
Diffusion model, a new generative modelling paradigm, has achieved great success in image, audio, and video generation. However, considering the discrete categorical nature of text…
HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation
Hongyi Yuan, Zheng Yuan, Chuanqi Tan +2
Language models with the Transformers structure have shown great performance in natural language processing. However, there still poses problems when fine-tuning pre-trained langua…
SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition
Jianing Wang, Chengcheng Han, Chengyu Wang +5
Few-shot Named Entity Recognition (NER) aims to identify named entities with very little annotated data. Previous methods solve this problem based on token-wise classification, whi…
A Survey on Open Information Extraction from Rule-based Model to Large Language Model
Pai Liu, Wenyang Gao, Wenjie Dong +7
Open Information Extraction (OpenIE) represents a crucial NLP task aimed at deriving structured information from unstructured text, unrestricted by relation type or domain. This su…
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections
Chenliang Li, Haiyang Xu, Junfeng Tian +12
Large-scale pretrained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstrea…
Parameter-Efficient Sparsity for Large Language Models Fine-Tuning
Yuchao Li, Fuli Luo, Chuanqi Tan +4
With the dramatically increased number of parameters in language models, sparsity methods have received ever-increasing research focus to compress and accelerate the models. While…
Towards Unified Prompt Tuning for Few-shot Text Classification
Jianing Wang, Chengyu Wang, Fuli Luo +6
Prompt-based fine-tuning has boosted the performance of Pre-trained Language Models (PLMs) on few-shot text classification by employing task-specific prompts. Yet, PLMs are unfamil…
Image Captioning In the Transformer Age
Yang Xu, Li Li, Haiyang Xu +3
Image Captioning (IC) has achieved astonishing developments by incorporating various techniques into the CNN-RNN encoder-decoder architecture. However, since CNN and RNN do not sha…
Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency
Yanyang Li, Fuli Luo, Runxin Xu +3
Structured pruning has been extensively studied on monolingual pre-trained language models and is yet to be fully evaluated on their multilingual counterparts. This work investigat…
Contrastive Demonstration Tuning for Pre-trained Language Models
Xiaozhuan Liang, Ningyu Zhang, Siyuan Cheng +3
Pretrained language models can be effectively stimulated by textual prompts or demonstrations, especially in low-data scenarios. Recent works have focused on automatically searchin…
Making Pre-trained Language Models End-to-end Few-shot Learners with Contrastive Prompt Tuning
Ziyun Xu, Chengyu Wang, Minghui Qiu +4
Pre-trained Language Models (PLMs) have achieved remarkable performance for various language understanding tasks in IR systems, which require the fine-tuning process based on label…
Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding
Zheng Yuan, Chuanqi Tan, Songfang Huang
Automatic ICD coding is defined as assigning disease codes to electronic medical records (EMRs). Existing methods usually apply label attention with code representations to match r…
From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression
Runxin Xu, Fuli Luo, Chengyu Wang +4
Pre-trained Language Models (PLMs) have achieved great success in various Natural Language Processing (NLP) tasks under the pre-training and fine-tuning paradigm. With large quanti…