Search Results for author: Lu Wang

Found 165 papers, 47 papers with code

Temporal Logic Point Processes

no code implementations ICML 2020 Shuang Li, Lu Wang, Ruizhi Zhang, xiaofu Chang, Xuqin Liu, Yao Xie, Yuan Qi, Le Song

We propose a modeling framework for event data, which excels in small data regime with the ability to incorporate domain knowledge.

Point Processes

Modeling Content Importance for Summarization with Pre-trained Language Models

no code implementations EMNLP 2020 Liqiang Xiao, Lu Wang, Hao He, Yaohui Jin

Previous work is mostly based on statistical methods that estimate word-level salience, which does not consider semantics and larger context when quantifying importance.

RuAG: Learned-rule-augmented Generation for Large Language Models

no code implementations4 Nov 2024 Yudi Zhang, Pei Xiao, Lu Wang, Chaoyun Zhang, Meng Fang, Yali Du, Yevgeniy Puzyrev, Randolph Yao, Si Qin, QIngwei Lin, Mykola Pechenizkiy, Dongmei Zhang, Saravan Rajmohan, Qi Zhang

In-context learning (ICL) and Retrieval-Augmented Generation (RAG) have gained attention for their ability to enhance LLMs' reasoning by incorporating external knowledge but suffer from limited contextual window size, leading to insufficient information injection.

Decision Making In-Context Learning +1

Self-Evolved Reward Learning for LLMs

no code implementations1 Nov 2024 Chenghua Huang, Zhizhen Fan, Lu Wang, Fangkai Yang, Pu Zhao, Zeqi Lin, QIngwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang

Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences, playing a pivotal role in the success of conversational models like GPT-4, ChatGPT, and Llama 2.

Deep Learning-Driven Microstructure Characterization and Vickers Hardness Prediction of Mg-Gd Alloys

no code implementations27 Oct 2024 Lu Wang, Hongchan Chen, Bing Wang, Qian Li, Qun Luo, Yuexing Han

This framework integrates both elemental composition and microstructural features to accurately predict the Vickers hardness of solid-solution Mg-Gd alloys.

Expanding Chatbot Knowledge in Customer Service: Context-Aware Similar Question Generation Using Large Language Models

no code implementations16 Oct 2024 Mengze Hong, Yuanfeng Song, Di Jiang, Lu Wang, Zichang Guo, Chen Jason Zhang

To accommodate potential variations in how a customer's query may be expressed, it emerges as the favored solution to augment these QA pairs with similar questions that are possibly diverse while remaining semantic consistency.

Chatbot Diversity +3

Closing the Loop: Learning to Generate Writing Feedback via Language Model Simulated Student Revisions

1 code implementation10 Oct 2024 Inderjeet Nair, Jiaye Tan, Xiaotian Su, Anne Gere, Xu Wang, Lu Wang

However, it remains unclear whether the feedback generated by these models is truly effective in enhancing the quality of student revisions.

Language Modelling

Narrative-of-Thought: Improving Temporal Reasoning of Large Language Models via Recounted Narratives

no code implementations7 Oct 2024 Xinliang Frederick Zhang, Nick Beauchamp, Lu Wang

In this work, we first study an essential task of temporal reasoning -- temporal graph generation, to unveil LLMs' inherent, global reasoning capabilities.

Graph Generation

Scalable Fine-tuning from Multiple Data Sources:A First-Order Approximation Approach

1 code implementation28 Sep 2024 Dongyue Li, Ziniu Zhang, Lu Wang, Hongyang R. Zhang

We study the problem of fine-tuning a language model (LM) for a target task by optimally using the information from $n$ auxiliary tasks.

Attack End-to-End Autonomous Driving through Module-Wise Noise

no code implementations12 Sep 2024 Lu Wang, Tianyuan Zhang, Yikai Han, Muyang Fang, Ting Jin, Jiaqi Kang

We conduct large-scale experiments on the full-stack autonomous driving model and demonstrate that our attack method outperforms previous attack methods.

Autonomous Driving

Module-wise Adaptive Adversarial Training for End-to-end Autonomous Driving

no code implementations11 Sep 2024 Tianyuan Zhang, Lu Wang, Jiaqi Kang, Xinwei Zhang, Siyuan Liang, Yuwei Chen, Aishan Liu, Xianglong Liu

Recent advances in deep learning have markedly improved autonomous driving (AD) models, particularly end-to-end systems that integrate perception, prediction, and planning stages, achieving state-of-the-art performance.

Autonomous Driving

Scaling Law with Learning Rate Annealing

no code implementations20 Aug 2024 Howe Tissue, Venus Wang, Lu Wang

We find that the cross-entropy loss curves of neural language models empirically adhere to a scaling law with learning rate (LR) annealing over training steps: $$L(s) = L_0 + A\cdot S_1^{-\alpha} - C\cdot S_2,$$ where $L(s)$ is the validation loss at step $s$, $S_1$ is the area under the LR curve, $S_2$ is the LR annealing area, and $L_0$, $A$, $C$, $\alpha$ are constant parameters.

Language Modelling

Multi-Scale Representation Learning for Image Restoration with State-Space Model

no code implementations19 Aug 2024 Yuhong He, Long Peng, Qiaosi Yi, Chen Wu, Lu Wang

Image restoration endeavors to reconstruct a high-quality, detail-rich image from a degraded counterpart, which is a pivotal process in photography and various computer vision systems.

Denoising Image Restoration +3

Gaussian Mixture based Evidential Learning for Stereo Matching

no code implementations5 Aug 2024 Weide Liu, Xingxing Wang, Lu Wang, Jun Cheng, Fayao Liu, Xulei Yang

In this paper, we introduce a novel Gaussian mixture based evidential learning solution for robust stereo matching.

Depth Estimation Stereo Matching

Can LLMs "Reason" in Music? An Evaluation of LLMs' Capability of Music Understanding and Generation

no code implementations31 Jul 2024 Ziya Zhou, Yuhang Wu, Zhiyue Wu, Xinyue Zhang, Ruibin Yuan, Yinghao Ma, Lu Wang, Emmanouil Benetos, Wei Xue, Yike Guo

Yet scant research explores the details of how these LLMs perform on advanced music understanding and conditioned generation, especially from the multi-step reasoning perspective, which is a critical aspect in the conditioned, editable, and interactive human-computer co-creation process.

Micro-Expression Recognition by Motion Feature Extraction based on Pre-training

no code implementations10 Jul 2024 Ruolin Li, Lu Wang, Tingting Yang, Lisheng Xu, Bingyang Ma, Yongchun Li, Hongchao Wei

To enable the model to more effectively separate features, we utilize the extracted motion features and the texture features from the onset frame to reconstruct the apex frame.

Micro Expression Recognition Micro-Expression Recognition

AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation

no code implementations27 Jun 2024 Jia Fu, Xiaoting Qin, Fangkai Yang, Lu Wang, Jue Zhang, QIngwei Lin, Yubo Chen, Dongmei Zhang, Saravan Rajmohan, Qi Zhang

Recent advancements in Large Language Models have transformed ML/AI development, necessitating a reevaluation of AutoML principles for the Retrieval-Augmented Generation (RAG) systems.

AutoML Efficient Exploration +3

Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding

no code implementations19 Jun 2024 Xin Liu, Farima Fatahi Bayat, Lu Wang

Built on top of ActCab, we further propose CoDec, a confidence-guided decoding strategy to elicit truthful answers with high confidence from LMs.

Language Modelling TruthfulQA

Verifiable Generation with Subsentence-Level Fine-Grained Citations

no code implementations10 Jun 2024 Shuyang Cao, Lu Wang

Verifiable generation requires large language models (LLMs) to cite source documents supporting their outputs, thereby improve output transparency and trustworthiness.

Sentence Specificity

LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions

no code implementations3 Jun 2024 Tianyuan Zhang, Lu Wang, Hainan Li, Yisong Xiao, Siyuan Liang, Aishan Liu, Xianglong Liu, DaCheng Tao

For the first time, this paper studies the potential threats caused by these environmental illusions to LD and establishes the first comprehensive benchmark LanEvil for evaluating the robustness of LD against this natural corruption.

Autonomous Driving Benchmarking +1

A Mallows-like Criterion for Anomaly Detection with Random Forest Implementation

no code implementations29 May 2024 Gaoxiang Zhao, Lu Wang, Xiaoqiang Wang

The effectiveness of anomaly signal detection can be significantly undermined by the inherent uncertainty of relying on one specified model.

Anomaly Detection

Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning

1 code implementation26 May 2024 Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang, QIngwei Lin, Alois Knoll, Ming Jin

In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent safety constraints.

Multi-Objective Reinforcement Learning reinforcement-learning +1

Maximizing Information Gain in Privacy-Aware Active Learning of Email Anomalies

no code implementations13 May 2024 Mu-Huan Miles Chung, Sharon Li, Jaturong Kongmanee, Lu Wang, Yuhong Yang, Calvin Giang, Khilan Jerath, Abhay Raman, David Lie, Mark Chignell

We also recommend that the information gain maximizing sample method (based on expert confidence) should be used in early stages of Active Learning, providing that well-calibrated confidence can be obtained.

Active Learning

MIDGARD: Self-Consistency Using Minimum Description Length for Structured Commonsense Reasoning

1 code implementation8 May 2024 Inderjeet Nair, Lu Wang

We study the task of conducting structured reasoning as generating a reasoning graph from natural language input using large language models (LLMs).

Graph Generation Missing Elements

Real-time Neural Woven Fabric Rendering

no code implementations4 May 2024 Xiang Chen, Lu Wang, Beibei Wang

Thanks to the regularity and repetitiveness of woven fabric patterns, our network can encode fabric patterns and parameters as a small latent vector, which is later interpreted by a small decoder, enabling the representation of different types of fabrics.

Decoder

Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expression

1 code implementation1 May 2024 Farima Fatahi Bayat, Xin Liu, H. V. Jagadish, Lu Wang

The adaptive nature of LITO counters the limitations of one-size-fits-all intervention methods, maximizing truthfulness by reflecting the model's internal knowledge only when it is confident.

Language Modelling Question Answering

Small Language Models Need Strong Verifiers to Self-Correct Reasoning

1 code implementation26 Apr 2024 Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim, Moontae Lee, Honglak Lee, Lu Wang

Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs), where LLMs refine their solutions using self-generated critiques that pinpoint the errors.

Math

Source-Aware Training Enables Knowledge Attribution in Language Models

1 code implementation1 Apr 2024 Muhammad Khalifa, David Wadden, Emma Strubell, Honglak Lee, Lu Wang, Iz Beltagy, Hao Peng

We investigate the problem of intrinsic source citation, where LLMs are required to cite the pretraining source supporting a generated response.

Data Augmentation

CODA: A COst-efficient Test-time Domain Adaptation Mechanism for HAR

no code implementations22 Mar 2024 Minghui Qiu, Yandao Huang, Lin Chen, Lu Wang, Kaishun Wu

In recent years, emerging research on mobile sensing has led to novel scenarios that enhance daily life for humans, but dynamic usage conditions often result in performance degradation when systems are deployed in real-world settings.

Active Learning Domain Adaptation +2

Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection

1 code implementation20 Mar 2024 Xincheng Yao, Ruoqi Li, Zefeng Qian, Lu Wang, Chongyang Zhang

In this paper, we propose a novel Hierarchical Gaussian mixture normalizing flow modeling method for accomplishing unified Anomaly Detection, which we call HGAD.

Anomaly Detection

Dual-Path Coupled Image Deraining Network via Spatial-Frequency Interaction

1 code implementation7 Feb 2024 Yuhong He, Aiwen Jiang, Lingfang Jiang, Zhifeng Wang, Lu Wang

Transformers have recently emerged as a significant force in the field of image deraining.

Rain Removal

COIN: Chance-Constrained Imitation Learning for Uncertainty-aware Adaptive Resource Oversubscription Policy

no code implementations13 Jan 2024 Lu Wang, Mayukh Das, Fangkai Yang, Chao Duo, Bo Qiao, Hang Dong, Si Qin, Chetan Bansal, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

We address the challenge of learning safe and robust decision policies in presence of uncertainty in context of the real scientific problem of adaptive resource oversubscription to enhance resource efficiency while ensuring safety against resource congestion risk.

Imitation Learning Management

Contrastive Learning with Negative Sampling Correction

no code implementations13 Jan 2024 Lu Wang, Chao Du, Pu Zhao, Chuan Luo, Zhangchi Zhu, Bo Qiao, Wei zhang, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

To correct the negative sampling bias, we propose a novel contrastive learning method named Positive-Unlabeled Contrastive Learning (PUCL).

Contrastive Learning Data Augmentation +2

Parallel Ranking of Ads and Creatives in Real-Time Advertising Systems

no code implementations20 Dec 2023 Zhiguang Yang, Lu Wang, Chun Gan, Liufang Sang, Haoran Wang, Wenlong Chen, Jie He, Changping Peng, Zhangang Lin, Jingping Shao

In this paper, we propose for the first time a novel architecture for online parallel estimation of ads and creatives ranking, as well as the corresponding offline joint optimization model.

Marketing

TaskWeaver: A Code-First Agent Framework

1 code implementation29 Nov 2023 Bo Qiao, Liqun Li, Xu Zhang, Shilin He, Yu Kang, Chaoyun Zhang, Fangkai Yang, Hang Dong, Jue Zhang, Lu Wang, Minghua Ma, Pu Zhao, Si Qin, Xiaoting Qin, Chao Du, Yong Xu, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang

TaskWeaver provides support for rich data structures, flexible plugin usage, and dynamic plugin selection, and leverages LLM coding capabilities for complex logic.

Natural Language Understanding

MOKA: Moral Knowledge Augmentation for Moral Event Extraction

1 code implementation16 Nov 2023 Xinliang Frederick Zhang, Winston Wu, Nick Beauchamp, Lu Wang

News media often strive to minimize explicit moral language in news articles, yet most articles are dense with moral values as expressed through the reported events themselves.

Event Extraction Moral Scenarios

PELMS: Pre-training for Effective Low-Shot Multi-Document Summarization

1 code implementation16 Nov 2023 Joseph J. Peper, Wenzhao Qiu, Lu Wang

We investigate pre-training techniques for abstractive multi-document summarization (MDS), which is much less studied than summarizing single documents.

Document Summarization General Knowledge +2

Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation

1 code implementation7 Nov 2023 Ruomeng Ding, Chaoyun Zhang, Lu Wang, Yong Xu, Minghua Ma, Wei zhang, Si Qin, Saravan Rajmohan, QIngwei Lin, Dongmei Zhang

To address these limitations, we introduce a novel thought prompting approach called "Everything of Thoughts" (XoT) to defy the law of "Penrose triangle of existing thought paradigms.

Decision Making

LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses

1 code implementation30 Oct 2023 Xin Liu, Muhammad Khalifa, Lu Wang

For evaluation, we construct CaT, a benchmark consisting of eight text generation tasks, covering responses ranging from short phrases to paragraphs.

Language Modelling Text Generation

All Things Considered: Detecting Partisan Events from News Media with Cross-Article Comparison

no code implementations28 Oct 2023 Yujian Liu, Xinliang Frederick Zhang, Kaijian Zou, Ruihong Huang, Nick Beauchamp, Lu Wang

Public opinion is shaped by the information news media provide, and that information in turn may be shaped by the ideological preferences of media outlets.

A quantum segmentation algorithm based on local adaptive threshold for NEQR image

no code implementations2 Oct 2023 Lu Wang, Wenjie Liu

In this paper, a quantum segmentation algorithm based on local adaptive threshold for NEQR image is proposed, which can use quantum mechanism to simultaneously compute local thresholds for all pixels in a gray-scale image and quickly segment the image into a binary image.

Binarization Image Segmentation +1

Quantum Image Segmentation Based on Grayscale Morphology

no code implementations2 Oct 2023 Wenjie Liu, Lu Wang, Mengmeng Cui

The classical image segmentation algorithm based on grayscale morphology can effectively segment images with uneven illumination, but with the increase of the image data, the real-time problem will emerge.

Image Segmentation Segmentation +1

Quantum image edge detection based on eight-direction Sobel operator for NEQR

no code implementations1 Oct 2023 Wenjie Liu, Lu Wang

However, the existing QSED algorithms only consider two- or four-direction Sobel operator, which leads to a certain loss of edge detail information in some high-definition images.

Edge Detection

A quantum moving target segmentation algorithm for grayscale video

no code implementations1 Oct 2023 Wenjie Liu, Lu Wang, Qingshan Wu

For a quantum video with $2^m$ frames (every frame is a $2^n\times 2^n$ image with $q$ grayscale levels), the complexity of our algorithm can be reduced to O$(n^2 + q)$.

Binarization Segmentation

Interpretable Imitation Learning with Dynamic Causal Relations

no code implementations30 Sep 2023 Tianxiang Zhao, Wenchao Yu, Suhang Wang, Lu Wang, Xiang Zhang, Yuncong Chen, Yanchi Liu, Wei Cheng, Haifeng Chen

After the model is learned, we can obtain causal relations among states and action variables behind its decisions, exposing policies learned by it.

Causal Discovery Imitation Learning

On-device Real-time Custom Hand Gesture Recognition

no code implementations19 Sep 2023 Esha Uboweja, David Tian, Qifei Wang, Yi-Chun Kuo, Joe Zou, Lu Wang, George Sung, Matthias Grundmann

Our framework provides a pre-trained single-hand embedding model that can be fine-tuned for custom gesture recognition.

Hand Gesture Recognition Hand-Gesture Recognition

Latent Degradation Representation Constraint for Single Image Deraining

1 code implementation9 Sep 2023 Yuhong He, Long Peng, Lu Wang, Jun Cheng

Since rain streaks show a variety of shapes and directions, learning the degradation representation is extremely challenging for single image deraining.

Decoder Representation Learning +1

Exploring Demonstration Ensembling for In-context Learning

1 code implementation17 Aug 2023 Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang

The standard approach for ICL is to prompt the LM with concatenated demonstrations followed by the test input.

In-Context Learning

Reinforcement Logic Rule Learning for Temporal Point Processes

no code implementations11 Aug 2023 Chao Yang, Lu Wang, Kun Gao, Shuang Li

Leveraging the temporal point process modeling and learning framework, the rule content and weights will be gradually optimized until the likelihood of the observational event sequences is optimal.

Point Processes

Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correction

1 code implementation1 Aug 2023 Zhangchi Zhu, Lu Wang, Pu Zhao, Chao Du, Wei zhang, Hang Dong, Bo Qiao, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang

To mitigate the impact of label uncertainty and improve the robustness of learning with positive and unlabeled data, we propose a new robust PU learning method with a training strategy motivated by the nature of human learning: easy cases should be learned first.

A ground-based dataset and a diffusion model for on-orbit low-light image enhancement

no code implementations25 Jun 2023 Yiman Zhu, Lu Wang, Jingyi Yuan, Yu Guo

To evenly sample poses of different orientation and distance without collision, a collision-free working space and pose stratified sampling is proposed.

Denoising Diversity +1

Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations

1 code implementation13 Jun 2023 Tianxiang Zhao, Wenchao Yu, Suhang Wang, Lu Wang, Xiang Zhang, Yuncong Chen, Yanchi Liu, Wei Cheng, Haifeng Chen

Imitation learning has achieved great success in many sequential decision-making tasks, in which a neural agent is learned by imitating collected human demonstrations.

Disentanglement Imitation Learning

GRACE: Discriminator-Guided Chain-of-Thought Reasoning

1 code implementation24 May 2023 Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang

To address this issue, we propose Guiding chain-of-thought ReAsoning with a CorrectnEss Discriminator (GRACE), a stepwise decoding approach that steers the decoding process towards producing correct reasoning steps.

GSM8K Math

Scientific Opinion Summarization: Paper Meta-review Generation Dataset, Methods, and Evaluation

1 code implementation24 May 2023 Qi Zeng, Mankeerat Sidhu, Ansel Blume, Hou Pong Chan, Lu Wang, Heng Ji

To address this gap, we propose the task of scientific opinion summarization, where research paper reviews are synthesized into meta-reviews.

Opinion Summarization Review Generation +1

AWESOME: GPU Memory-constrained Long Document Summarization using Memory Mechanism and Global Salient Content

no code implementations24 May 2023 Shuyang Cao, Lu Wang

Long document summarization systems are critical for domains with lengthy and jargonladen text, yet they present significant challenges to researchers and developers with limited computing resources.

Document Summarization document understanding +1

Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering

1 code implementation19 May 2023 Fangkai Yang, Pu Zhao, Zezhong Wang, Lu Wang, Jue Zhang, Mohit Garg, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang

Large Language Model (LLM) has gained popularity and achieved remarkable results in open-domain tasks, but its performance in real industrial domain-specific scenarios is average due to its lack of specific domain knowledge.

Language Modelling Large Language Model +2

Introspective Tips: Large Language Model for In-Context Decision Making

no code implementations19 May 2023 Liting Chen, Lu Wang, Hang Dong, Yali Du, Jie Yan, Fangkai Yang, Shuang Li, Pu Zhao, Si Qin, Saravan Rajmohan, QIngwei Lin, Dongmei Zhang

The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks.

Decision Making Language Modelling +2

BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases

2 code implementations19 May 2023 Xin Liu, Muhammad Khalifa, Lu Wang

Energy-based models (EBMs) have gained popularity for controlled text generation due to their high applicability to a wide range of constraints.

Text Generation

Implementing Active Learning in Cybersecurity: Detecting Anomalies in Redacted Emails

no code implementations1 Mar 2023 Mu-Huan Chung, Lu Wang, Sharon Li, Yuhong Yang, Calvin Giang, Khilan Jerath, Abhay Raman, David Lie, Mark Chignell

In this paper we present research results concerning the application of Active Learning to anomaly detection in redacted emails, comparing the utility of different methods for implementing active learning in this context.

Active Learning Anomaly Detection

Conservative State Value Estimation for Offline Reinforcement Learning

1 code implementation NeurIPS 2023 Liting Chen, Jie Yan, Zhengdao Shao, Lu Wang, QIngwei Lin, Saravan Rajmohan, Thomas Moscibroda, Dongmei Zhang

In this paper, we propose Conservative State Value Estimation (CSVE), a new approach that learns conservative V-function via directly imposing penalty on OOD states.

D4RL reinforcement-learning +1

Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning

no code implementations21 Nov 2022 Junjie Sheng, Lu Wang, Fangkai Yang, Bo Qiao, Hang Dong, Xiangfeng Wang, Bo Jin, Jun Wang, Si Qin, Saravan Rajmohan, QIngwei Lin, Dongmei Zhang

To address these two limitations, this paper formulates the oversubscription for cloud as a chance-constrained optimization problem and propose an effective Chance Constrained Multi-Agent Reinforcement Learning (C2MARL) method to solve this problem.

Multi-agent Reinforcement Learning reinforcement-learning +2

Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure

1 code implementation14 Nov 2022 Joseph J. Peper, Lu Wang

Generative models have demonstrated impressive results on Aspect-based Sentiment Analysis (ABSA) tasks, particularly for the emerging task of extracting Aspect-Category-Opinion-Sentiment (ACOS) quadruples.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2

Late Fusion with Triplet Margin Objective for Multimodal Ideology Prediction and Analysis

no code implementations4 Nov 2022 Changyuan Qiu, Winston Wu, Xinliang Frederick Zhang, Lu Wang

In this work, we introduce the task of multimodal ideology prediction, where a model predicts binary or five-point scale ideological leanings, given a text-image pair with political content.

Triplet

Time-aware Prompting for Text Generation

no code implementations3 Nov 2022 Shuyang Cao, Lu Wang

Despite having less performance drop when testing on data drawn from a later time, linear prompts focus more on non-temporal information and are less sensitive to the given timestamps, according to human evaluations and sensitivity analyses.

Data-to-Text Generation

Generative Entity-to-Entity Stance Detection with Knowledge Graph Augmentation

1 code implementation2 Nov 2022 Xinliang Frederick Zhang, Nick Beauchamp, Lu Wang

We present a novel generative framework to allow the generation of canonical names for entities as well as stances among them.

Sentence Stance Detection

Joint Communication and Sensing in RIS-enabled mmWave Networks

no code implementations7 Oct 2022 Lu Wang, Luis F. Abanto-Leon, Arash Asadi

Empowering cellular networks with augmented sensing capabilities is one of the key research areas in 6G communication systems.

A Fast Algorithm for Onboard Atmospheric Powered Descent Guidance

no code implementations9 Sep 2022 Yushu Chen, Guangwen Yang, Lu Wang, Qingzhong Gan, Haipeng Chen, Quanyong Xu

Atmospheric powered descent guidance can be solved by successive convexification; however, its onboard application is impeded by the sharp increase in computation caused by nonlinear aerodynamic forces.

Extensive Study of Multiple Deep Neural Networks for Complex Random Telegraph Signals

no code implementations31 May 2022 Marcel Robitaille, HeeBong Yang, Lu Wang, Na Young Kim

Time-fluctuating signals are ubiquitous and diverse in many physical, chemical, and biological systems, among which random telegraph signals (RTSs) refer to a series of instantaneous switching events between two discrete levels from single-particle movements.

Transfer Learning

Few-shot Reranking for Multi-hop QA via Language Model Prompting

2 code implementations25 May 2022 Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang

To alleviate the need for a large number of labeled question-document pairs for retriever training, we propose PromptRank, which relies on large language models prompting for multi-hop path reranking.

Open-Domain Question Answering Passage Re-Ranking +2

Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needs

1 code implementation NAACL 2022 Xu Wang, Simin Fan, Jessica Houghton, Lu Wang

NLP-powered automatic question generation (QG) techniques carry great pedagogical potential of saving educators' time and benefiting student learning.

Misconceptions Question Generation +1

Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model

no code implementations7 Apr 2022 Nick J. C. Wang, Lu Wang, Yandan Sun, Haimei Kang, Dejun Zhang

We revisit ideas presented by Lugosch et al. using speech pre-training and three-module modeling; however, to ease construction of the end-to-end SLU model, we use as our phoneme module an open-source acoustic-phonetic model from a DNN-HMM hybrid automatic speech recognition (ASR) system instead of training one from scratch.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Efficient Argument Structure Extraction with Transfer Learning and Active Learning

no code implementations Findings (ACL) 2022 Xinyu Hua, Lu Wang

Combined with transfer learning, substantial F1 score boost (5-25) can be further achieved during the early iterations of active learning across domains.

Active Learning Transfer Learning

HIBRIDS: Attention with Hierarchical Biases for Structure-aware Long Document Summarization

no code implementations ACL 2022 Shuyang Cao, Lu Wang

In this work, we present HIBRIDS, which injects Hierarchical Biases foR Incorporating Document Structure into the calculation of attention scores.

Document Summarization

Anchor Graph Structure Fusion Hashing for Cross-Modal Similarity Search

no code implementations9 Feb 2022 Lu Wang, Jie Yang, Masoumeh Zareapoor, ZhongLong Zheng

Cross-modal hashing still has some challenges needed to address: (1) most existing CMH methods take graphs as input to model data distribution.

Retrieval

Auto robust relative radiometric normalization via latent change noise modelling

no code implementations24 Nov 2021 Shiqi Liu, Lu Wang, Jie Lian, Ting Chen, Cong Liu, Xuchen Zhan, Jintao Lu, Jie Liu, Ting Wang, Dong Geng, Hongwei Duan, Yuze Tian

Relative radiometric normalization(RRN) of different satellite images of the same terrain is necessary for change detection, object classification/segmentation, and map-making tasks.

Change Detection

Rapid Assessments of Light-Duty Gasoline Vehicle Emissions Using On-Road Remote Sensing and Machine Learning

no code implementations1 Oct 2021 Yan Xia, Linhui Jiang, Lu Wang, Xue Chen, Jianjie Ye, Tangyan Hou, Liqiang Wang, Yibo Zhang, Mengying Li, Zhen Li, Zhe Song, Yaping Jiang, Weiping Liu, Pengfei Li, Daniel Rosenfeld, John H. Seinfeld, Shaocai Yu

Our results show that the ORRS measurements, assisted by the machine-learning-based ensemble model developed here, can realize day-to-day supervision of on-road vehicle-specific emissions.

Controllable Summarization with Constrained Markov Decision Process

1 code implementation7 Aug 2021 Hou Pong Chan, Lu Wang, Irwin King

We study controllable text summarization which allows users to gain control on a particular attribute (e. g., length limit) of the generated summaries.

Attribute Text Summarization

Controllable Open-ended Question Generation with A New Question Type Ontology

1 code implementation ACL 2021 Shuyang Cao, Lu Wang

We first define a new question type ontology which differentiates the nuanced nature of questions better than widely used question words.

Diversity Question Generation +2

An Efficient Group-based Search Engine Marketing System for E-Commerce

no code implementations24 Jun 2021 Cheng Jie, Da Xu, Zigeng Wang, Lu Wang, Wei Shen

With the increasing scale of search engine marketing, designing an efficient bidding system is becoming paramount for the success of e-commerce companies.

Marketing

Understanding the Spread of COVID-19 Epidemic: A Spatio-Temporal Point Process View

no code implementations24 Jun 2021 Shuang Li, Lu Wang, Xinyun Chen, Yixiang Fang, Yan Song

In this paper, we model the propagation of the COVID-19 as spatio-temporal point processes and propose a generative and intensity-free model to track the spread of the disease.

Imitation Learning Point Processes

Learning To Segment Actions From Visual and Language Instructions via Differentiable Weak Sequence Alignment

1 code implementation CVPR 2021 YuHan Shen, Lu Wang, Ehsan Elhamifar

We address the problem of unsupervised localization of key-steps and feature learning in instructional videos using both visual and language instructions.

LoRA: Low-Rank Adaptation of Large Language Models

61 code implementations ICLR 2022 Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen

We propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks.

Ranked #2 on parameter-efficient fine-tuning on HellaSwag (using extra training data)

Language Modelling parameter-efficient fine-tuning

DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation

no code implementations ACL 2021 Xinyu Hua, Ashwin Sreevatsa, Lu Wang

To enrich the generation with diverse content, we further propose to use large pre-trained models to predict relevant concepts and to generate claims.

Text Generation

TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning

3 code implementations17 May 2021 Lu Wang, xiaofu Chang, Shuang Li, Yunfei Chu, Hui Li, Wei zhang, Xiaofeng He, Le Song, Jingren Zhou, Hongxia Yang

Secondly, on top of the proposed graph transformer, we introduce a two-stream encoder that separately extracts representations from temporal neighborhoods associated with the two interaction nodes and then utilizes a co-attentional transformer to model inter-dependencies at a semantic level.

Contrastive Learning Graph Learning +2

Unsupervised Learning of Multi-level Structures for Anomaly Detection

no code implementations25 Apr 2021 Songmin Dai, Jide Li, Lu Wang, Congcong Zhu, Yifan Wu, Xiaoqiang Li

This paper first introduces a novel method to generate anomalous data by breaking up global structures while preserving local structures of normal data at multiple levels.

Anomaly Detection

Attention Head Masking for Inference Time Content Selection in Abstractive Summarization

no code implementations NAACL 2021 Shuyang Cao, Lu Wang

Using attention head masking, we are able to reveal the relation between encoder-decoder attentions and content selection behaviors of summarization models.

Abstractive Text Summarization Decoder +1

Efficient Attentions for Long Document Summarization

1 code implementation NAACL 2021 Luyang Huang, Shuyang Cao, Nikolaus Parulian, Heng Ji, Lu Wang

The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization.

Decoder Document Summarization

Inference Time Style Control for Summarization

no code implementations NAACL 2021 Shuyang Cao, Lu Wang

How to generate summaries of different styles without requiring corpora in the target styles, or training separate models?

Decoder

MD-MTL: An Ensemble Med-Multi-Task Learning Package for DiseaseScores Prediction and Multi-Level Risk Factor Analysis

no code implementations5 Mar 2021 Lu Wang, Haoyan Jiang, Mark Chignell

In this paper, we developed a new ensemble machine learning Python package based on multi-task learning (MTL), referred to as the Med-Multi-Task Learning (MD-MTL) package and applied it in predicting disease scores of patients, and in carrying out risk factor analysis on multiple subgroups of patients simultaneously.

BIG-bench Machine Learning Multi-Task Learning

Annotation-Efficient Learning for Medical Image Segmentation based on Noisy Pseudo Labels and Adversarial Learning

no code implementations29 Dec 2020 Lu Wang, Dong Guo, Guotai Wang, Shaoting Zhang

In this paper, we propose an annotation-efficient learning framework for segmentation tasks that avoids annotations of training images, where we use an improved Cycle-Consistent Generative Adversarial Network (GAN) to learn from a set of unpaired medical images and auxiliary masks obtained either from a shape model or public datasets.

Generative Adversarial Network Image Segmentation +3

Adaptive Federated Learning and Digital Twin for Industrial Internet of Things

no code implementations25 Oct 2020 Wen Sun, Shiyu Lei, Lu Wang, Zhiqiang Liu, Yan Zhang

Industrial Internet of Things (IoT) enables distributed intelligent services varying with the dynamic and realtime industrial devices to achieve Industry 4. 0 benefits.

Clustering Federated Learning +1

PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation

no code implementations EMNLP 2020 Xinyu Hua, Lu Wang

In this work, we present a novel content-controlled text generation framework, PAIR, with planning and iterative refinement, which is built upon a large model, BART.

Sentence Text Generation

Dynamic Online Conversation Recommendation

no code implementations ACL 2020 Xingshan Zeng, Jing Li, Lu Wang, Zhiming Mao, Kam-Fai Wong

Trending topics in social media content evolve over time, and it is therefore crucial to understand social media users and their interpersonal communications in a dynamic manner.

XREF: Entity Linking for Chinese News Comments with Supplementary Article Reference

no code implementations AKBC 2020 Xinyu Hua, Lei LI, Lifeng Hua, Lu Wang

We therefore propose a novel model, XREF, that leverages attention mechanisms to (1) pinpoint relevant context within comments, and (2) detect supporting entities from the news article.

Entity Linking

Vision-Based Fall Event Detection in Complex Background Using Attention Guided Bi-directional LSTM

no code implementations24 Jun 2020 Yong Chen, Lu Wang, Jiajia Hu, Mingbin Ye

Fall event detection, as one of the greatest risks to the elderly, has been a hot research issue in the solitary scene in recent years.

Event Detection

Provably Robust Metric Learning

2 code implementations NeurIPS 2020 Lu Wang, Xuanqing Liu, Jin-Feng Yi, Yuan Jiang, Cho-Jui Hsieh

Metric learning is an important family of algorithms for classification and similarity search, but the robustness of learned metrics against small adversarial perturbations is less studied.

Metric Learning

Spanning Attack: Reinforce Black-box Attacks with Unlabeled Data

1 code implementation11 May 2020 Lu Wang, huan zhang, Jin-Feng Yi, Cho-Jui Hsieh, Yuan Jiang

By constraining adversarial perturbations in a low-dimensional subspace via spanning an auxiliary unlabeled dataset, the spanning attack significantly improves the query efficiency of a wide variety of existing black-box attacks.

Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward

1 code implementation ACL 2020 Luyang Huang, Lingfei Wu, Lu Wang

Sequence-to-sequence models for abstractive summarization have been studied extensively, yet the generated summaries commonly suffer from fabricated content, and are often found to be near-extractive.

Abstractive Text Summarization Cloze Test +1

Weakly-supervised 3D coronary artery reconstruction from two-view angiographic images

no code implementations26 Mar 2020 Lu Wang, Dong-Xue Liang, Xiao-Lei Yin, Jing Qiu, Zhi-Yun Yang, Jun-Hui Xing, Jian-Zeng Dong, Zhao-Yuan Ma

The reconstruction of three-dimensional models of coronary arteries is of great significance for the localization, evaluation and diagnosis of stenosis and plaque in the arteries, as well as for the assisted navigation of interventional surgery.

3D Reconstruction Vocal Bursts Valence Prediction +1

Coronary Artery Segmentation in Angiographic Videos Using A 3D-2D CE-Net

no code implementations26 Mar 2020 Lu Wang, Dong-Xue Liang, Xiao-Lei Yin, Jing Qiu, Zhi-Yun Yang, Jun-Hui Xing, Jian-Zeng Dong, Zhao-Yuan Ma

This article proposes a new video segmentation framework that can extract the clearest and most comprehensive coronary angiography images from a video sequence, thereby helping physicians to better observe the condition of blood vessels.

Coronary Artery Segmentation Segmentation +2

Asymmetric Correlation Quantization Hashing for Cross-modal Retrieval

no code implementations14 Jan 2020 Lu Wang, Jie Yang

Due to the superiority in similarity computation and database storage for large-scale multiple modalities data, cross-modal hashing methods have attracted extensive attention in similarity retrieval across the heterogeneous modalities.

Cross-Modal Retrieval Quantization +1

Cluster-wise Unsupervised Hashing for Cross-Modal Similarity Search

no code implementations11 Nov 2019 Lu Wang, Jie Yang

Large-scale cross-modal hashing similarity retrieval has attracted more and more attention in modern search applications such as search engines and autopilot, showing great superiority in computation and storage.

Clustering Retrieval

Neural Conversation Recommendation with Online Interaction Modeling

no code implementations IJCNLP 2019 Xingshan Zeng, Jing Li, Lu Wang, Kam-Fai Wong

The prevalent use of social media leads to a vast amount of online conversations being produced on a daily basis.

Collaborative Filtering

Infinite-horizon Off-Policy Policy Evaluation with Multiple Behavior Policies

no code implementations ICLR 2020 Xinyun Chen, Lu Wang, Yizhe Hang, Heng Ge, Hongyuan Zha

We consider off-policy policy evaluation when the trajectory data are generated by multiple behavior policies.

Learning Robust Representations with Graph Denoising Policy Network

no code implementations4 Oct 2019 Lu Wang, Wenchao Yu, Wei Wang, Wei Cheng, Wei zhang, Hongyuan Zha, Xiaofeng He, Haifeng Chen

Graph representation learning, aiming to learn low-dimensional representations which capture the geometric dependencies between nodes in the original graph, has gained increasing popularity in a variety of graph analysis tasks, including node classification and link prediction.

Denoising Graph Representation Learning +3

In Plain Sight: Media Bias Through the Lens of Factual Reporting

1 code implementation IJCNLP 2019 Lisa Fan, Marshall White, Eva Sharma, Ruisi Su, Prafulla Kumar Choubey, Ruihong Huang, Lu Wang

The increasing prevalence of political bias in news media calls for greater public awareness of it, as well as robust methods for its detection.

An Entity-Driven Framework for Abstractive Summarization

no code implementations IJCNLP 2019 Eva Sharma, Luyang Huang, Zhe Hu, Lu Wang

Human judges further rate our system summaries as more informative and coherent than those by popular summarization models.

Abstractive Text Summarization Document Summarization +2

Sentence-Level Content Planning and Style Specification for Neural Text Generation

no code implementations IJCNLP 2019 Xinyu Hua, Lu Wang

Building effective text generation systems requires three critical components: content selection, text planning, and surface realization, and traditionally they are tackled as separate problems.

Decoder Sentence +1

Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards

1 code implementation ACL 2019 Hou Pong Chan, Wang Chen, Lu Wang, Irwin King

To address this problem, we propose a reinforcement learning (RL) approach for keyphrase generation, with an adaptive reward function that encourages a model to generate both sufficient and accurate keyphrases.

Keyphrase Generation reinforcement-learning +2

Evaluating the Robustness of Nearest Neighbor Classifiers: A Primal-Dual Perspective

1 code implementation10 Jun 2019 Lu Wang, Xuanqing Liu, Jin-Feng Yi, Zhi-Hua Zhou, Cho-Jui Hsieh

Furthermore, we show that dual solutions for these QP problems could give us a valid lower bound of the adversarial perturbation that can be used for formal robustness verification, giving us a nice view of attack/verification for NN models.

valid

BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization

no code implementations ACL 2019 Eva Sharma, Chen Li, Lu Wang

Most existing text summarization datasets are compiled from the news domain, where summaries have a flattened discourse structure.

Text Summarization

Joint Effects of Context and User History for Predicting Online Conversation Re-entries

1 code implementation ACL 2019 Xingshan Zeng, Jing Li, Lu Wang, Kam-Fai Wong

We hypothesize that both the context of the ongoing conversations and the users' previous chatting history will affect their continued interests in future engagement.

Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization

no code implementations ACL 2019 Hai Ye, Wenjie Li, Lu Wang

Semantic parsing aims to transform natural language (NL) utterances into formal meaning representations (MRs), whereas an NL generator achieves the reverse: producing a NL description for some given MRs.

Code Generation Dialogue Management +2

Optimal margin Distribution Network

no code implementations ICLR 2019 Shen-Huan Lv, Lu Wang, Zhi-Hua Zhou

Recent research about margin theory has proved that maximizing the minimum margin like support vector machines does not necessarily lead to better performance, and instead, it is crucial to optimize the margin distribution.

IvaNet: Learning to jointly detect and segment objets with the help of Local Top-Down Modules

no code implementations18 Mar 2019 Shihua Huang, Lu Wang

Driven by Convolutional Neural Networks, object detection and semantic segmentation have gained significant improvements.

object-detection Object Detection +1

Improving Generalization of Deep Neural Networks by Leveraging Margin Distribution

1 code implementation ICLR 2019 Shen-Huan Lyu, Lu Wang, Zhi-Hua Zhou

We utilize a convex margin distribution loss function on the deep neural networks to validate our theoretical results by optimizing the margin ratio.

Representation Learning

Learning Segmentation Masks with the Independence Prior

no code implementations12 Nov 2018 Songmin Dai, Xiaoqiang Li, Lu Wang, Pin Wu, Weiqin Tong, Yimin Chen

We get appealing results in both tasks, which shows the independence prior is useful for instance segmentation and it is possible to unsupervisedly learn instance masks with only one image.

Foreground Segmentation Instance Segmentation +3

Hull Form Optimization with Principal Component Analysis and Deep Neural Network

no code implementations27 Oct 2018 Dongchi Yu, Lu Wang

Designing and modifying complex hull forms for optimal vessel performances have been a major challenge for naval architects.

Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information

no code implementations14 Oct 2018 Lisa Fan, Dong Yu, Lu Wang

Sequence-to-sequence (seq2seq) neural models have been actively investigated for abstractive summarization.

Abstractive Text Summarization