b'Xu Sun'

research

∙ 09/11/2023

Incorporating Pre-trained Model Prompting in Multimodal Stock Volume Movement Prediction

Multimodal stock trading volume movement prediction with stock-related n...

0 Ruibo Chen, et al. ∙

research

∙ 08/25/2023

MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning

Supervised visual captioning models typically require a large scale of i...

0 Bang Yang, et al. ∙

research

∙ 07/29/2023

Towards Codable Text Watermarking for Large Language Models

As large language models (LLMs) generate texts with increasing fluency a...

0 Lean Wang, et al. ∙

research

∙ 06/07/2023

M^3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning

Instruction tuning has significantly advanced large language models (LLM...

0 Lei Li, et al. ∙

research

∙ 05/23/2023

Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

In-context learning (ICL) emerges as a promising capability of large lan...

0 Lean Wang, et al. ∙

research

∙ 05/23/2023

Can Language Models Understand Physical Concepts?

Language models (LMs) gradually become general-purpose interfaces in the...

0 Lei Li, et al. ∙

research

∙ 05/21/2023

Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter

Federated Multilingual Neural Machine Translation (Fed-MNMT) has emerged...

2 YI LIU, et al. ∙

research

∙ 05/13/2023

PALM: Open Fundus Photograph Dataset with Pathologic Myopia Recognition and Anatomical Structure Annotation

Pathologic myopia (PM) is a common blinding retinal degeneration suffere...

6 Huihui Fang, et al. ∙

research

∙ 05/08/2023

Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias

Pre-trained Language Models (PLMs) may be poisonous with backdoors or bi...

0 Zhiyuan Zhang, et al. ∙

research

∙ 04/10/2023

Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition

This work proposes POMP, a prompt pre-training method for vision-languag...

4 Shuhuai Ren, et al. ∙

research

∙ 01/30/2023

Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features

Detecting out-of-distribution (OOD) inputs is crucial for the safe deplo...

0 Sishuo Chen, et al. ∙

research

∙ 01/25/2023

When to Trust Aggregated Gradients: Addressing Negative Client Sampling in Federated Learning

Federated Learning has become a widely-used framework which allows learn...

0 Wenkai Yang, et al. ∙

research

∙ 01/25/2023

Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learning

Federated Learning (FL) has become a popular distributed learning paradi...

0 Wenkai Yang, et al. ∙

research

∙ 12/31/2022

A Survey for In-context Learning

With the increasing ability of large language models (LLMs), in-context ...

0 Qingxiu Dong, et al. ∙

research

∙ 11/22/2022

Aligning Source Visual and Target Language Domains for Unpaired Video Captioning

Training supervised video captioning model requires coupled video-captio...

0 Fenglin Liu, et al. ∙

research

∙ 11/02/2022

Gradient Knowledge Distillation for Pre-trained Language Models

Knowledge distillation (KD) is an effective framework to transfer knowle...

0 Lean Wang, et al. ∙

research

∙ 10/28/2022

DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention

Vision-and-language (V-L) tasks require the system to understand both vi...

0 Fenglin Liu, et al. ∙

research

∙ 10/23/2022

Retrieve, Reason, and Refine: Generating Accurate and Faithful Patient Instructions

The "Patient Instruction" (PI), which contains critical instructional in...

0 Fenglin Liu, et al. ∙

research

∙ 10/19/2022

Prophet Attention: Predicting Attention with Future Attention for Improved Image Captioning

Recently, attention based models have been used extensively in many sequ...

5 Fenglin Liu, et al. ∙

research

∙ 10/18/2022

Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attac...

0 Zhiyuan Zhang, et al. ∙

research

∙ 10/14/2022

Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks

Natural language processing (NLP) models are known to be vulnerable to b...

1 Sishuo Chen, et al. ∙

research

∙ 10/14/2022

Holistic Sentence Embeddings for Better Out-of-Distribution Detection

Detecting out-of-distribution (OOD) instances is significant for the saf...

9 Sishuo Chen, et al. ∙

research

∙ 10/13/2022

GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization

Recently, Sharpness-Aware Minimization (SAM) algorithm has shown state-o...

19 Zhiyuan Zhang, et al. ∙

research

∙ 10/13/2022

Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation

Despite the potential of federated learning, it is known to be vulnerabl...

5 Zhiyuan Zhang, et al. ∙

research

∙ 10/11/2022

From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models

Investigating better ways to reuse the released pre-trained language mod...

14 Lei Li, et al. ∙

research

∙ 06/04/2022

Rethinking the Openness of CLIP

Contrastive Language-Image Pre-training (CLIP) has demonstrated great po...

14 Shuhuai Ren, et al. ∙

research

∙ 03/20/2022

Hierarchical Inductive Transfer for Continual Dialogue Learning

Pre-trained models have achieved excellent performance on the dialogue t...

1 Shaoxiong Feng, et al. ∙

research

∙ 03/12/2022

DFTR: Depth-supervised Hierarchical Feature Fusion Transformer for Salient Object Detection

Automated salient object detection (SOD) plays an increasingly crucial r...

14 Heqin Zhu, et al. ∙

research

∙ 02/18/2022

REFUGE2 Challenge: Treasure for Multi-Domain Learning in Glaucoma Assessment

Glaucoma is the second leading cause of blindness and is the leading cau...

13 Huihui Fang, et al. ∙

research

∙ 02/16/2022

ADAM Challenge: Detecting Age-related Macular Degeneration from Fundus Images

Age-related macular degeneration (AMD) is the leading cause of visual im...

11 Huihui Fang, et al. ∙

research

∙ 12/14/2021

Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models

As many fine-tuned pre-trained language models (PLMs) with promising per...

7 Lei Li, et al. ∙

research

∙ 11/26/2021

KNAS: Green Neural Architecture Search

Many existing neural architecture search (NAS) solutions rely on downstr...

8 Jingjing Xu, et al. ∙

research

∙ 11/08/2021

Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation

Medical report generation, which aims to automatically generate a long a...

17 Fenglin Liu, et al. ∙

research

∙ 10/15/2021

RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models

Backdoor attacks, which maliciously control a well-trained model's outpu...

4 Wenkai Yang, et al. ∙

research

∙ 10/13/2021

Well-classified Examples are Underestimated in Classification with Deep Neural Networks

The conventional wisdom behind learning deep classification models is to...

5 Guangxiang Zhao, et al. ∙

research

∙ 10/08/2021

Topology-Imbalance Learning for Semi-Supervised Node Classification

The class imbalance problem, as an important issue in learning node repr...

6 Deli Chen, et al. ∙

research

∙ 09/23/2021

Dynamic Knowledge Distillation for Pre-trained Language Models

Knowledge distillation (KD) has been proved effective for compressing la...

0 Lei Li, et al. ∙

research

∙ 09/07/2021

Adversarial Parameter Defense by Multi-Step Risk Minimization

Previous studies demonstrate DNNs' vulnerability to adversarial examples...

3 Zhiyuan Zhang, et al. ∙

research

∙ 09/03/2021

How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data

Since training a large-scale backdoored model from scratch requires a la...

2 Zhiyuan Zhang, et al. ∙

research

∙ 09/01/2021

Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification

Data augmentation aims to enrich training samples for alleviating the ov...

10 Shuhuai Ren, et al. ∙

research

∙ 08/23/2021

Long-term, Short-term and Sudden Event: Trading Volume Movement Prediction with Graph-based Multi-view Modeling

Trading volume movement prediction is the key in a variety of financial ...

6 Liang Zhao, et al. ∙

research

∙ 08/20/2021

ASAT: Adaptively Scaled Adversarial Training in Time Series

Adversarial training is a method for enhancing neural networks to improv...

0 Zhiyuan Zhang, et al. ∙

research

∙ 08/05/2021

O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning

Video captioning combines video understanding and language generation. D...

6 Fenglin Liu, et al. ∙

research

∙ 06/13/2021

Contrastive Attention for Automatic Chest X-ray Report Generation

Recently, chest X-ray report generation, which aims to automatically gen...

16 Fenglin Liu, et al. ∙

research

∙ 05/28/2021

Learning Relation Alignment for Calibrated Cross-modal Retrieval

Despite the achievements of large-scale multimodal pre-training approach...

7 Shuhuai Ren, et al. ∙

research

∙ 05/28/2021

Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge

Knowledge facts are typically represented by relational triples, while w...

10 Yi Zhang, et al. ∙

research

∙ 05/15/2021

Rethinking Skip Connection with Layer Normalization in Transformers and ResNets

Skip connection, is a widely-used technique to improve the performance a...

53 Fenglin Liu, et al. ∙

research

∙ 03/29/2021

Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models

Recent studies have revealed a security threat to natural language proce...

2 Wenkai Yang, et al. ∙

research

∙ 02/22/2021

Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillation

Neural dialogue models suffer from low-quality responses when interacted...

2 Shaoxiong Feng, et al. ∙

research

∙ 12/29/2020

Accelerating Pre-trained Language Models via Calibrated Cascade

Dynamic early exiting aims to accelerate pre-trained language models' (P...

6 Lei Li, et al. ∙

Xu Sun

Featured Co-authors