Search Results for author: Xingxing Zhang

Found 49 papers, 20 papers with code

MathScale: Scaling Instruction Tuning for Mathematical Reasoning

no code implementations5 Mar 2024 Zhengyang Tang, Xingxing Zhang, Benyou Wan, Furu Wei

Inspired by the cognitive mechanism in human mathematical learning, it first extracts topics and knowledge points from seed math questions and then build a concept graph, which is subsequently used to generate new math questions.

GSM8K Math +1

DualTeacher: Bridging Coexistence of Unlabelled Classes for Semi-supervised Incremental Object Detection

1 code implementation13 Dec 2023 Ziqi Yuan, Liyuan Wang, Wenbo Ding, Xingxing Zhang, Jiachen Zhong, Jianyong Ai, Jianmin Li, Jun Zhu

A commonly-used strategy for supervised IOD is to encourage the current model (as a student) to mimic the behavior of the old model (as a teacher), but it generally fails in SSIOD because a dominant number of object instances from old and new classes are coexisting and unlabelled, with the teacher only recognizing a fraction of them.

Object object-detection +1

Unleashing the potential of GNNs via Bi-directional Knowledge Transfer

no code implementations26 Oct 2023 Shuai Zheng, Zhizhe Liu, Zhenfeng Zhu, Xingxing Zhang, JianXin Li, Yao Zhao

On this basis, BiKT not only allows us to acquire knowledge from both the GNN and its derived model but promotes each other by injecting the knowledge into the other.

Domain Adaptation Representation Learning +1

Towards a General Framework for Continual Learning with Pre-training

1 code implementation21 Oct 2023 Liyuan Wang, Jingyi Xie, Xingxing Zhang, Hang Su, Jun Zhu

In this work, we present a general framework for continual learning of sequentially arrived tasks with the use of pre-training, which has emerged as a promising direction for artificial intelligence systems to accommodate real-world dynamics.

Continual Learning

Tuna: Instruction Tuning using Feedback from Large Language Models

1 code implementation20 Oct 2023 Haoran Li, Yiran Liu, Xingxing Zhang, Wei Lu, Furu Wei

Furthermore, we apply probabilistic ranking and contextual ranking sequentially to the instruction-tuned LLM.

Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality

1 code implementation NeurIPS 2023 Liyuan Wang, Jingyi Xie, Xingxing Zhang, Mingyi Huang, Hang Su, Jun Zhu

Following these empirical and theoretical insights, we propose Hierarchical Decomposition (HiDe-)Prompt, an innovative approach that explicitly optimizes the hierarchical components with an ensemble of task-specific prompts and statistics of both uninstructed and instructed representations, further with the coordination of a contrastive regularization strategy.

Continual Learning

Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence

1 code implementation29 Aug 2023 Liyuan Wang, Xingxing Zhang, Qian Li, Mingtian Zhang, Hang Su, Jun Zhu, Yi Zhong

Continual learning aims to empower artificial intelligence (AI) with strong adaptability to the real world.

Continual Learning

LongNet: Scaling Transformers to 1,000,000,000 Tokens

3 code implementations5 Jul 2023 Jiayu Ding, Shuming Ma, Li Dong, Xingxing Zhang, Shaohan Huang, Wenhui Wang, Nanning Zheng, Furu Wei

Scaling sequence length has become a critical demand in the era of large language models.

A Comprehensive Survey of Continual Learning: Theory, Method and Application

1 code implementation31 Jan 2023 Liyuan Wang, Xingxing Zhang, Hang Su, Jun Zhu

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime.

Continual Learning Learning Theory

Momentum Calibration for Text Generation

no code implementations8 Dec 2022 Xingxing Zhang, Yiran Liu, Xun Wang, Pengcheng He, Yang Yu, Si-Qing Chen, Wayne Xiong, Furu Wei

The input and output of most text generation tasks can be transformed to two sequences of tokens and they can be modeled using sequence-to-sequence learning modeling tools such as Transformers.

Abstractive Text Summarization Text Generation

Latent Prompt Tuning for Text Summarization

no code implementations3 Nov 2022 Yubo Zhang, Xingxing Zhang, Xun Wang, Si-Qing Chen, Furu Wei

In this paper, we propose Lotus (shorthand for Latent Prompt Tuning for Summarization), which is a single model that can be applied in both controlled and uncontrolled (without control signals) modes.

Contrastive Learning Text Summarization

HVS-Inspired Signal Degradation Network for Just Noticeable Difference Estimation

1 code implementation16 Aug 2022 Jian Jin, Yuan Xue, Xingxing Zhang, Lili Meng, Yao Zhao, Weisi Lin

However, they have a major drawback that the generated JND is assessed in the real-world signal domain instead of in the perceptual domain in the human brain.

Diagnosing Ensemble Few-Shot Classifiers

no code implementations9 Jun 2022 Weikai Yang, Xi Ye, Xingxing Zhang, Lanxi Xiao, Jiazhi Xia, Zhongyuan Wang, Jun Zhu, Hanspeter Pfister, Shixia Liu

The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance.

Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization

no code implementations ACL 2022 Ruipeng Jia, Xingxing Zhang, Yanan Cao, Shi Wang, Zheng Lin, Furu Wei

In zero-shot multilingual extractive text summarization, a model is typically trained on English summarization dataset and then applied on summarization datasets of other languages.

Extractive Summarization Extractive Text Summarization +1

Memory Replay with Data Compression for Continual Learning

1 code implementation ICLR 2022 Liyuan Wang, Xingxing Zhang, Kuo Yang, Longhui Yu, Chongxuan Li, Lanqing Hong, Shifeng Zhang, Zhenguo Li, Yi Zhong, Jun Zhu

In this work, we propose memory replay with data compression (MRDC) to reduce the storage cost of old training samples and thus increase their amount that can be stored in the memory buffer.

Autonomous Driving Class Incremental Learning +5

Auto-Weighted Layer Representation Based View Synthesis Distortion Estimation for 3-D Video Coding

no code implementations7 Jan 2022 Jian Jin, Xingxing Zhang, Lili Meng, Weisi Lin, Jie Liang, Huaxiang Zhang, Yao Zhao

Experimental results show that the VSD can be accurately estimated with the weights learnt by the nonlinear mapping function once its associated S-VSDs are available.

Sequence Level Contrastive Learning for Text Summarization

no code implementations8 Sep 2021 Shusheng Xu, Xingxing Zhang, Yi Wu, Furu Wei

In this paper, we propose a contrastive learning model for supervised abstractive text summarization, where we view a document, its gold summary and its model generated summaries as different views of the same mean representation and maximize the similarities between them during training.

Abstractive Text Summarization Contrastive Learning +2

Double Low-Rank Representation With Projection Distance Penalty for Clustering

no code implementations CVPR 2021 Zhiqiang Fu, Yao Zhao, Dongxia Chang, Xingxing Zhang, Yiming Wang

This paper presents a novel, simple yet robust self-representation method, i. e., Double Low-Rank Representation with Projection Distance penalty (DLRRPD) for clustering.

Clustering

Attention Temperature Matters in Abstractive Summarization Distillation

1 code implementation ACL 2022 Shengqiang Zhang, Xingxing Zhang, Hangbo Bao, Furu Wei

In this paper, we find simply manipulating attention temperatures in Transformers can make pseudo labels easier to learn for student models.

Abstractive Text Summarization

Auto-weighted low-rank representation for clustering

no code implementations26 Apr 2021 Zhiqiang Fu, Yao Zhao, Dongxia Chang, Xingxing Zhang, Yiming Wang

In this paper, a novel unsupervised low-rank representation model, i. e., Auto-weighted Low-Rank Representation (ALRR), is proposed to construct a more favorable similarity graph (SG) for clustering.

Clustering Representation Learning

Just Noticeable Difference for Deep Machine Vision

no code implementations16 Feb 2021 Jian Jin, Xingxing Zhang, Xin Fu, huan zhang, Weisi Lin, Jian Lou, Yao Zhao

Experimental results on image classification demonstrate that we successfully find the JND for deep machine vision.

Image Classification Neural Network Security +1

Unsupervised Fine-tuning for Text Clustering

no code implementations COLING 2020 Shaohan Huang, Furu Wei, Lei Cui, Xingxing Zhang, Ming Zhou

Fine-tuning with pre-trained language models (e. g. BERT) has achieved great success in many language understanding tasks in supervised settings (e. g. text classification).

Clustering text-classification +2

Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction

no code implementations EMNLP 2020 Mengyun Chen, Tao Ge, Xingxing Zhang, Furu Wei, Ming Zhou

We propose a novel language-independent approach to improve the efficiency for Grammatical Error Correction (GEC) by dividing the task into two subtasks: Erroneous Span Detection (ESD) and Erroneous Span Correction (ESC).

Grammatical Error Correction Sentence

Taking Modality-free Human Identification as Zero-shot Learning

no code implementations2 Oct 2020 Zhizhe Liu, Xingxing Zhang, Zhenfeng Zhu, Shuai Zheng, Yao Zhao, Jian Cheng

There have been numerous methods proposed for human identification, such as face identification, person re-identification, and gait identification.

Attribute Event Detection +4

Pre-training for Abstractive Document Summarization by Reinstating Source Text

no code implementations EMNLP 2020 Yanyan Zou, Xingxing Zhang, Wei Lu, Furu Wei, Ming Zhou

The main idea is that, given an input text artificially constructed from a document, a model is pre-trained to reinstate the original document.

Abstractive Text Summarization Document Summarization +1

From Anchor Generation to Distribution Alignment: Learning a Discriminative Embedding Space for Zero-Shot Recognition

no code implementations10 Feb 2020 Fuzhen Li, Zhenfeng Zhu, Xingxing Zhang, Jian Cheng, Yao Zhao

In zero-shot learning (ZSL), the samples to be classified are usually projected into side information templates such as attributes.

Zero-Shot Learning

To See in the Dark: N2DGAN for Background Modeling in Nighttime Scene

no code implementations12 Dec 2019 Zhenfeng Zhu, Yingying Meng, Deqiang Kong, Xingxing Zhang, Yandong Guo, Yao Zhao

Due to the deteriorated conditions of \mbox{illumination} lack and uneven lighting, nighttime images have lower contrast and higher noise than their daytime counterparts of the same scene, which limits seriously the performances of conventional background modeling methods.

Understand Dynamic Regret with Switching Cost for Online Decision Making

no code implementations28 Nov 2019 Yawei Zhao, Qian Zhao, Xingxing Zhang, En Zhu, Xinwang Liu, Jianping Yin

We provide a new theoretical analysis framework, which shows an interesting observation, that is, the relation between the switching cost and the dynamic regret is different for settings of OA and OCO.

Decision Making Relation

DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue

1 code implementation17 Nov 2019 Xiaoze Jiang, Jing Yu, Zengchang Qin, Yingying Zhuang, Xingxing Zhang, Yue Hu, Qi Wu

More importantly, we can tell which modality (visual or semantic) has more contribution in answering the current question by visualizing the gate values.

feature selection Question Answering +2

Defensive Few-shot Learning

1 code implementation16 Nov 2019 Wenbin Li, Lei Wang, Xingxing Zhang, Lei Qi, Jing Huo, Yang Gao, Jiebo Luo

(2) how to narrow the distribution gap between clean and adversarial examples under the few-shot setting?

Adversarial Defense Few-Shot Learning

ATZSL: Defensive Zero-Shot Recognition in the Presence of Adversaries

no code implementations24 Oct 2019 Xingxing Zhang, Shupeng Gui, Zhenfeng Zhu, Yao Zhao, Ji Liu

In this paper, we take an initial attempt, and propose a generic formulation to provide a systematical solution (named ATZSL) for learning a robust ZSL model.

Image Captioning Object Recognition +2

Hierarchical Prototype Learning for Zero-Shot Recognition

no code implementations24 Oct 2019 Xingxing Zhang, Shupeng Gui, Zhenfeng Zhu, Yao Zhao, Ji Liu

Specifically, HPL is able to obtain discriminability on both seen and unseen class domains by learning visual prototypes respectively under the transductive setting.

Attribute Image Captioning +3

ProLFA: Representative Prototype Selection for Local Feature Aggregation

1 code implementation24 Oct 2019 Xingxing Zhang, Zhenfeng Zhu, Yao Zhao

Given a set of hand-crafted local features, acquiring a global representation via aggregation is a promising technique to boost computational efficiency and improve task performance.

Computational Efficiency Prototype Selection

Convolutional Prototype Learning for Zero-Shot Recognition

no code implementations22 Oct 2019 Zhizhe Liu, Xingxing Zhang, Zhenfeng Zhu, Shuai Zheng, Yao Zhao, Jian Cheng

The key to ZSL is to transfer knowledge from the seen to the unseen classes via auxiliary class attribute vectors.

Attribute Image Captioning +3

HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization

no code implementations ACL 2019 Xingxing Zhang, Furu Wei, Ming Zhou

Neural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods.

Document Summarization Extractive Summarization +2

Neural Latent Extractive Document Summarization

no code implementations EMNLP 2018 Xingxing Zhang, Mirella Lapata, Furu Wei, Ming Zhou

Extractive summarization models require sentence-level labels, which are usually created heuristically (e. g., with rule-based methods) given that most summarization datasets only have document-summary pairs.

Document Summarization Extractive Document Summarization +3

Dependency Parsing as Head Selection

1 code implementation EACL 2017 Xingxing Zhang, Jianpeng Cheng, Mirella Lapata

Conventional graph-based dependency parsers guarantee a tree structure both during training and inference.

Dependency Parsing Sentence

Top-down Tree Long Short-Term Memory Networks

1 code implementation NAACL 2016 Xingxing Zhang, Liang Lu, Mirella Lapata

Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have been successfully applied to a variety of sequence modeling tasks.

Dependency Parsing Sentence +1

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