1.4k citations · 2.2k across the 116 of their papers we have counts for
116 papers
LOGO: A Long-Form Video Dataset for Group Action Quality Assessment
Shiyi Zhang, Wenxun Dai, Sujia Wang +4
Action quality assessment (AQA) has become an emerging topic since it can be extensively applied in numerous scenarios. However, most existing methods and datasets focus on single-…
Introspective Deep Metric Learning
Chengkun Wang, Wenzhao Zheng, Zheng Zhu +2
This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images. Conventional deep metric learning methods focus on learning…
Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering
Yifan Dong, Suhang Wu, Fandong Meng +4
Multi-modal keyphrase generation aims to produce a set of keyphrases that represent the core points of the input text-image pair. In this regard, dominant methods mainly focus on m…
PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction
Sicheng Zuo, Wenzhao Zheng, Yuanhui Huang +2
Semantic segmentation in autonomous driving has been undergoing an evolution from sparse point segmentation to dense voxel segmentation, where the objective is to predict the seman…
Improving Translation Faithfulness of Large Language Models via Augmenting Instructions
Yijie Chen, Yijin Liu, Fandong Meng +3
Large Language Models (LLMs) present strong general capabilities, and a current compelling challenge is stimulating their specialized capabilities, such as machine translation, thr…
Instruction Position Matters in Sequence Generation with Large Language Models
Yijin Liu, Xianfeng Zeng, Fandong Meng +1
Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization, through instruction fine-tuning. The fine-tuning…
Towards Multiple References Era -- Addressing Data Leakage and Limited Reference Diversity in NLG Evaluation
Xianfeng Zeng, Yijin Liu, Fandong Meng +1
N-gram matching-based evaluation metrics, such as BLEU and chrF, are widely utilized across a range of natural language generation (NLG) tasks. However, recent studies have reveale…
An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
Yun Luo, Zhen Yang, Fandong Meng +3
Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information while acquiring new knowledge for achieving a satis…
Towards Codable Watermarking for Injecting Multi-bits Information to LLMs
Lean Wang, Wenkai Yang, Deli Chen +5
As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs. Text water…
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models
Ziyi Wang, Xumin Yu, Yongming Rao +2
With the overwhelming trend of mask image modeling led by MAE, generative pre-training has shown a remarkable potential to boost the performance of fundamental models in 2D vision.…
TIM: Teaching Large Language Models to Translate with Comparison
Jiali Zeng, Fandong Meng, Yongjing Yin +1
Open-sourced large language models (LLMs) have demonstrated remarkable efficacy in various tasks with instruction tuning. However, these models can sometimes struggle with tasks th…
Soft Language Clustering for Multilingual Model Pre-training
Jiali Zeng, Yufan Jiang, Yongjing Yin +5
Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language…
Mitigating Catastrophic Forgetting in Task-Incremental Continual Learning with Adaptive Classification Criterion
Yun Luo, Xiaotian Lin, Zhen Yang +3
Task-incremental continual learning refers to continually training a model in a sequence of tasks while overcoming the problem of catastrophic forgetting (CF). The issue arrives fo…
Unified Model Learning for Various Neural Machine Translation
Yunlong Liang, Fandong Meng, Jinan Xu +3
Existing neural machine translation (NMT) studies mainly focus on developing dataset-specific models based on data from different tasks (e.g., document translation and chat transla…
Towards Unifying Multi-Lingual and Cross-Lingual Summarization
Jiaan Wang, Fandong Meng, Duo Zheng +4
To adapt text summarization to the multilingual world, previous work proposes multi-lingual summarization (MLS) and cross-lingual summarization (CLS). However, these two tasks have…
RC3: Regularized Contrastive Cross-lingual Cross-modal Pre-training
Chulun Zhou, Yunlong Liang, Fandong Meng +3
Multilingual vision-language (V&L) pre-training has achieved remarkable progress in learning universal representations across different modalities and languages. In spite of recent…
WeLayout: WeChat Layout Analysis System for the ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents
Mingliang Zhang, Zhen Cao, Juntao Liu +3
In this paper, we introduce WeLayout, a novel system for segmenting the layout of corporate documents, which stands for WeChat Layout Analysis System. Our approach utilizes a sophi…
Investigating Forgetting in Pre-Trained Representations Through Continual Learning
Yun Luo, Zhen Yang, Xuefeng Bai +3
Representation forgetting refers to the drift of contextualized representations during continual training. Intuitively, the representation forgetting can influence the general know…
Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias
Zhiyuan Zhang, Deli Chen, Hao Zhou +3
Pre-trained Language Models (PLMs) may be poisonous with backdoors or bias injected by the suspicious attacker during the fine-tuning process. A core challenge of purifying potenti…
BranchNorm: Robustly Scaling Extremely Deep Transformers
Yijin Liu, Xianfeng Zeng, Fandong Meng +1
Recently, DeepNorm scales Transformers into extremely deep (i.e., 1000 layers) and reveals the promising potential of deep scaling. To stabilize the training of deep models, DeepNo…
Towards Accurate Post-training Quantization for Diffusion Models
Changyuan Wang, Ziwei Wang, Xiuwei Xu +3
In this paper, we propose an accurate data-free post-training quantization framework of diffusion models (ADP-DM) for efficient image generation. Conventional data-free quantizatio…
Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning
Lean Wang, Lei Li, Damai Dai +5
In-context learning (ICL) emerges as a promising capability of large language models (LLMs) by providing them with demonstration examples to perform diverse tasks. However, the und…
DTV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization
Yunlong Liang, Fandong Meng, Jiaan Wang +3
Many-to-many multimodal summarization (MS) task aims to generate summaries in any language with document inputs in any language and the corresponding image sequence, which esse…
Personality Understanding of Fictional Characters during Book Reading
Mo Yu, Jiangnan Li, Shunyu Yao +5
Comprehending characters' personalities is a crucial aspect of story reading. As readers engage with a story, their understanding of a character evolves based on new events and inf…