Search Results for author: Yang Liu

Found 1081 papers, 373 papers with code

Modeling Entity Knowledge for Fact Verification

no code implementations EMNLP (FEVER) 2021 Yang Liu, Chenguang Zhu, Michael Zeng

Fact verification is a challenging task of identifying the truthfulness of given claims based on the retrieval of relevant evidence texts.

Descriptive Fact Verification +1

Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs

no code implementations NAACL 2022 Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu, Dilek Hakkani-Tur

In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs.

Multi-Task Learning Response Generation +1

Interpolation between CNNs and ResNets

no code implementations ICML 2020 Zonghan Yang, Yang Liu, Chenglong Bao, Zuoqiang Shi

Although ordinary differential equations (ODEs) provide insights for designing networks architectures, its relationship with the non-residual convolutional neural networks (CNNs) is still unclear.

Adversarial Attack Image Classification

Amplifying Key Cues for Human-Object-Interaction Detection

no code implementations ECCV 2020 Yang Liu, Qingchao Chen, Andrew Zisserman

In this paper we introduce two methods to amplify key cues in the image, and also a method to combine these and other cues when considering the interaction between a human and an object.

Human-Object Interaction Detection Object

Personalized Entity Resolution with Dynamic Heterogeneous KnowledgeGraph Representations

no code implementations ACL (ECNLP) 2021 Ying Lin, Han Wang, Jiangning Chen, Tong Wang, Yue Liu, Heng Ji, Yang Liu, Premkumar Natarajan

We first build a cross-source heterogeneous knowledge graph from customer purchase history and product knowledge graph to jointly learn customer and product embeddings.

Entity Resolution

DialogSum Challenge: Summarizing Real-Life Scenario Dialogues

no code implementations INLG (ACL) 2021 Yulong Chen, Yang Liu, Yue Zhang

We propose a shared task on summarizing real-life scenario dialogues, DialogSum Challenge, to encourage researchers to address challenges in dialogue summarization, which has been less studied by the summarization community.

Common Sense Reasoning Representation Learning

Leveraging Seq2seq Language Generation for Multi-level Product Issue Identification

no code implementations ECNLP (ACL) 2022 Yang Liu, Varnith Chordia, Hua Li, Siavash Fazeli Dehkordy, Yifei Sun, Vincent Gao, Na Zhang

To harness such information to better serve customers, in this paper, we created a machine learning approach to automatically identify product issues and uncover root causes from the customer feedback text.

Multi-Label Classification Text Generation +1

Rethinking Data Augmentation in Text-to-text Paradigm

no code implementations COLING 2022 Yanan Chen, Yang Liu

As manually labelling data can be costly, some recent studies tend to augment the training data for improving the generalization power of machine learning models, known as data augmentation (DA).

Data Augmentation

Self-Supervised Quality Estimation for Machine Translation

no code implementations EMNLP 2021 Yuanhang Zheng, Zhixing Tan, Meng Zhang, Mieradilijiang Maimaiti, Huanbo Luan, Maosong Sun, Qun Liu, Yang Liu

Quality estimation (QE) of machine translation (MT) aims to evaluate the quality of machine-translated sentences without references and is important in practical applications of MT.

Machine Translation Sentence +1

Effective Convolutional Attention Network for Multi-label Clinical Document Classification

no code implementations EMNLP 2021 Yang Liu, Hua Cheng, Russell Klopfer, Matthew R. Gormley, Thomas Schaaf

Multi-label document classification (MLDC) problems can be challenging, especially for long documents with a large label set and a long-tail distribution over labels.

Classification Document Classification +1

Exploring Word Segmentation and Medical Concept Recognition for Chinese Medical Texts

1 code implementation NAACL (BioNLP) 2021 Yang Liu, Yuanhe Tian, Tsung-Hui Chang, Song Wu, Xiang Wan, Yan Song

Chinese word segmentation (CWS) and medical concept recognition are two fundamental tasks to process Chinese electronic medical records (EMRs) and play important roles in downstream tasks for understanding Chinese EMRs.

Chinese Word Segmentation Model Selection +1

中美学者学术英语写作中词汇难度特征比较研究——以计算语言学领域论文为例(A Comparative Study of the Features of Lexical Sophistication in Academic English Writing by Chinese and American)

no code implementations CCL 2021 Yonghui Xie, Yang Liu, Erhong Yang, Liner Yang

“学术英语写作在国际学术交流中的作用日益凸显, 然而对于英语非母语者, 学术英语写作是困难的, 为此本文对计算语言领域中美学者学术英语写作中词汇难度特征做比较研究。自构建1132篇中美论文全文语料库, 统计语料中484个词汇难度特征值。经过特征筛选与因子分析的降维处理得到表现较好的五个维度。最后计算中美学者论文的维度分从而比较差异, 发现美国学者的论文相较中国学者的论文中词汇单位更具常用性、二元词串更具稳固性、三元词串更具稳固性、虚词更具复杂性、词类更具关联性。主要原因在于统计特征值时借助的外部资源库与美国学者的论文更贴近, 且中国学者没有完全掌握该领域学术写作的习惯。因此, 中国学者可充分利用英语本族语者构建的资源库, 从而产出更为地道与流利的学术英语论文。”

A Hybrid System for NLPTEA-2020 CGED Shared Task

no code implementations AACL (NLP-TEA) 2020 Meiyuan Fang, Kai Fu, JiPing Wang, Yang Liu, Jin Huang, Yitao Duan

As a result, among the six tracks in the shared task, our system performs well in the correction tracks: measured in F1 score, we rank first, with the highest precision, in the TOP3 correction track and third in the TOP1 correction track, also with the highest precision.

基于词信息嵌入的汉语构词结构识别研究(Chinese Word-Formation Prediction based on Representations of Word-Related Features)

no code implementations CCL 2021 Hua Zheng, Yaqi Yan, Yue Wang, Damai Dai, Yang Liu

“作为一种意合型语言, 汉语中的构词结构刻画了构词成分之间的组合关系, 是认知、理解词义的关键。在中文信息处理领域, 此前的构词结构识别工作大多沿用句法层面的粗粒度标签, 且主要基于上下文等词间信息建模, 忽略了语素义、词义等词内信息对构词结构识别的作用。本文采用语言学视域下的构词结构标签体系, 构建汉语构词结构及相关信息数据集, 提出了一种基于Bi-LSTM和Self-attention的模型, 以此来探究词内、词间等多方面信息对构词结构识别的潜在影响和能达到的性能。实验取得了良好的预测效果, 准确率77. 87%, F1值78. 36%;同时, 对比测试揭示, 词内的语素义信息对构词结构识别具有显著的贡献, 而词间的上下文信息贡献较弱且带有较强的不稳定性。该预测方法与数据集, 将为中文信息处理的多种任务, 如语素和词结构分析、词义识别与生成、语言文字研究与词典编纂等提供新的观点和方案。”

EMIE-MAP: Large-Scale Road Surface Reconstruction Based on Explicit Mesh and Implicit Encoding

no code implementations18 Mar 2024 Wenhua Wu, Qi Wang, Guangming Wang, JunPing Wang, Tiankun Zhao, Yang Liu, Dongchao Gao, Zhe Liu, Hesheng Wang

To address this, we propose EMIE-MAP, a novel method for large-scale road surface reconstruction based on explicit mesh and implicit encoding.

NEDS-SLAM: A Novel Neural Explicit Dense Semantic SLAM Framework using 3D Gaussian Splatting

no code implementations18 Mar 2024 Yiming Ji, Yang Liu, Guanghu Xie, Boyu Ma, Zongwu Xie

We propose NEDS-SLAM, an Explicit Dense semantic SLAM system based on 3D Gaussian representation, that enables robust 3D semantic mapping, accurate camera tracking, and high-quality rendering in real-time.

Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification

1 code implementation15 Mar 2024 Pingping Zhang, Yuhao Wang, Yang Liu, Zhengzheng Tu, Huchuan Lu

To address above issues, we propose a novel learning framework named \textbf{EDITOR} to select diverse tokens from vision Transformers for multi-modal object ReID.

Object

Learning to Watermark LLM-generated Text via Reinforcement Learning

no code implementations13 Mar 2024 Xiaojun Xu, Yuanshun Yao, Yang Liu

While prior works focus on token-level watermark that embeds signals into the output, we design a model-level watermark that embeds signals into the LLM weights, and such signals can be detected by a paired detector.

StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models

1 code implementation12 Mar 2024 Zhicheng Guo, Sijie Cheng, Hao Wang, Shihao Liang, Yujia Qin, Peng Li, Zhiyuan Liu, Maosong Sun, Yang Liu

The virtual API server contains a caching system and API simulators which are complementary to alleviate the change in API status.

Benchmarking

Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards

no code implementations12 Mar 2024 Wei Shen, Xiaoying Zhang, Yuanshun Yao, Rui Zheng, Hongyi Guo, Yang Liu

Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences.

reinforcement-learning

ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval

no code implementations11 Mar 2024 Yuanhang Zheng, Peng Li, Wei Liu, Yang Liu, Jian Luan, Bin Wang

Specifically, our proposed ToolRerank includes Adaptive Truncation, which truncates the retrieval results related to seen and unseen tools at different positions, and Hierarchy-Aware Reranking, which makes retrieval results more concentrated for single-tool queries and more diverse for multi-tool queries.

Retrieval

SuPRA: Surgical Phase Recognition and Anticipation for Intra-Operative Planning

no code implementations10 Mar 2024 Maxence Boels, Yang Liu, Prokar Dasgupta, Alejandro Granados, Sebastien Ourselin

In conclusion, SuPRA presents a new multi-task approach that paves the way for improved intra-operative assistance through surgical phase recognition and prediction of future events.

Surgical phase recognition

Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation

no code implementations8 Mar 2024 Xiaoying Zhang, Jean-Francois Ton, Wei Shen, Hongning Wang, Yang Liu

We introduce Adversarial Policy Optimization (AdvPO), a novel solution to the pervasive issue of reward over-optimization in Reinforcement Learning from Human Feedback (RLHF) for Large Language Models (LLMs).

Towards Multimodal Sentiment Analysis Debiasing via Bias Purification

no code implementations8 Mar 2024 Dingkang Yang, Mingcheng Li, Dongling Xiao, Yang Liu, Kun Yang, Zhaoyu Chen, Yuzheng Wang, Peng Zhai, Ke Li, Lihua Zhang

In the inference phase, given a factual multimodal input, MCIS imagines two counterfactual scenarios to purify and mitigate these biases.

counterfactual Counterfactual Inference +1

On the Effectiveness of Distillation in Mitigating Backdoors in Pre-trained Encoder

1 code implementation6 Mar 2024 Tingxu Han, Shenghan Huang, Ziqi Ding, Weisong Sun, Yebo Feng, Chunrong Fang, Jun Li, Hanwei Qian, Cong Wu, Quanjun Zhang, Yang Liu, Zhenyu Chen

Distillation aims to distill knowledge from a given model (a. k. a the teacher net) and transfer it to another (a. k. a the student net).

Image Classification

A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Network

1 code implementation6 Mar 2024 Ruichen Ma, Guanchao Qiao, Yian Liu, Liwei Meng, Ning Ning, Yang Liu, Shaogang Hu

A&B BNN is proposed to directly remove part of the multiplication operations in a traditional BNN and replace the rest with an equal number of bit operations, introducing the mask layer and the quantized RPReLU structure based on the normalizer-free network architecture.

Image Classification

DomainVerse: A Benchmark Towards Real-World Distribution Shifts For Tuning-Free Adaptive Domain Generalization

no code implementations5 Mar 2024 Feng Hou, Jin Yuan, Ying Yang, Yang Liu, Yang Zhang, Cheng Zhong, Zhongchao shi, Jianping Fan, Yong Rui, Zhiqiang He

With the recent advance of vision-language models (VLMs), viewed as natural source models, the cross-domain task changes to directly adapt the pre-trained source model to arbitrary target domains equipped with prior domain knowledge, and we name this task Adaptive Domain Generalization (ADG).

Domain Generalization

FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio

1 code implementation4 Mar 2024 Chao Xu, Yang Liu, Jiazheng Xing, Weida Wang, Mingze Sun, Jun Dan, Tianxin Huang, Siyuan Li, Zhi-Qi Cheng, Ying Tai, Baigui Sun

In this paper, we abstract the process of people hearing speech, extracting meaningful cues, and creating various dynamically audio-consistent talking faces, termed Listening and Imagining, into the task of high-fidelity diverse talking faces generation from a single audio.

Disentanglement

PHAnToM: Personality Has An Effect on Theory-of-Mind Reasoning in Large Language Models

no code implementations4 Mar 2024 Fiona Anting Tan, Gerard Christopher Yeo, Fanyou Wu, Weijie Xu, Vinija Jain, Aman Chadha, Kokil Jaidka, Yang Liu, See-Kiong Ng

Drawing inspiration from psychological research on the links between certain personality traits and Theory-of-Mind (ToM) reasoning, and from prompt engineering research on the hyper-sensitivity of prompts in affecting LLMs capabilities, this study investigates how inducing personalities in LLMs using prompts affects their ToM reasoning capabilities.

Prompt Engineering

LoLiSRFlow: Joint Single Image Low-light Enhancement and Super-resolution via Cross-scale Transformer-based Conditional Flow

no code implementations29 Feb 2024 Ziyu Yue, Jiaxin Gao, Sihan Xie, Yang Liu, Zhixun Su

The visibility of real-world images is often limited by both low-light and low-resolution, however, these issues are only addressed in the literature through Low-Light Enhancement (LLE) and Super- Resolution (SR) methods.

Super-Resolution

Deep Learning for 3D Human Pose Estimation and Mesh Recovery: A Survey

1 code implementation29 Feb 2024 Yang Liu, Changzhen Qiu, Zhiyong Zhang

To the best of our knowledge, this survey is arguably the first to comprehensively cover deep learning methods for 3D human pose estimation, including both single-person and multi-person approaches, as well as human mesh recovery, encompassing methods based on explicit models and implicit representations.

3D Human Pose Estimation Autonomous Driving +1

PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation

no code implementations28 Feb 2024 Haoyu Xie, Changqi Wang, Jian Zhao, Yang Liu, Jun Dan, Chong Fu, Baigui Sun

To address this issue, we propose a robust contrastive-based S4 framework, termed the Probabilistic Representation Contrastive Learning (PRCL) framework to enhance the robustness of the unsupervised training process.

Contrastive Learning Semi-Supervised Semantic Segmentation

Datasets for Large Language Models: A Comprehensive Survey

1 code implementation28 Feb 2024 Yang Liu, Jiahuan Cao, Chongyu Liu, Kai Ding, Lianwen Jin

Additionally, a comprehensive review of the existing available dataset resources is also provided, including statistics from 444 datasets, covering 8 language categories and spanning 32 domains.

Language Modelling Large Language Model

ArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks

no code implementations27 Feb 2024 Yang Liu, Xiaomin Yu, Gongyu Zhang, Christos Bergeles, Prokar Dasgupta, Alejandro Granados, Sebastien Ourselin

We train models for these tasks in a zero-shot cross-modal transfer setting, a domain where the previous state-of-the-art method relied on the fixed scale noise injection, often compromising the semantic content of the original modality embedding.

Domain Generalization Image Captioning +3

Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models

no code implementations27 Feb 2024 Xiaolong Wang, Yile Wang, Yuanchi Zhang, Fuwen Luo, Peng Li, Maosong Sun, Yang Liu

Based on the characteristics of the tasks and the strong dialogue-generation capabilities of LLMs, we propose RiC (Reasoning in Conversation), a method that focuses on solving subjective tasks through dialogue simulation.

Dark Humor Detection Dialogue Generation +3

Dataset Fairness: Achievable Fairness on Your Data With Utility Guarantees

no code implementations27 Feb 2024 Muhammad Faaiz Taufiq, Jean-Francois Ton, Yang Liu

In machine learning fairness, training models which minimize disparity across different sensitive groups often leads to diminished accuracy, a phenomenon known as the fairness-accuracy trade-off.

Fairness

Citation-Enhanced Generation for LLM-based Chatbots

no code implementations25 Feb 2024 Weitao Li, Junkai Li, Weizhi Ma, Yang Liu

Note that our method is a training-free plug-and-play plugin that is capable of various LLMs.

Chatbot Citation Prediction +3

Budget-Constrained Tool Learning with Planning

1 code implementation25 Feb 2024 Yuanhang Zheng, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

Despite intensive efforts devoted to tool learning, the problem of budget-constrained tool learning, which focuses on resolving user queries within a specific budget constraint, has been widely overlooked.

Local stochastic computing using memristor-enabled stochastic logics

no code implementations25 Feb 2024 Lekai Song, Pengyu Liu, Jingfang Pei, Yang Liu, Songwei Liu, Shengbo Wang, Leonard W. T. Ng, Tawfique Hasan, Kong-Pang Pun, Shuo Gao, Guohua Hu

Stochastic computing offers a probabilistic approach to address challenges posed by problems with uncertainty and noise in various fields, particularly machine learning.

Autonomous Driving Edge Detection +1

LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper

no code implementations24 Feb 2024 Daoyuan Wu, Shuai Wang, Yang Liu, Ning Liu

Our key insight is that regardless of the kind of jailbreak strategies employed, they eventually need to include a harmful prompt (e. g., "how to make a bomb") in the prompt sent to LLMs, and we found that existing LLMs can effectively recognize such harmful prompts that violate their safety policies.

Adversarial Attack

Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA

1 code implementation24 Feb 2024 Wentao Mo, Yang Liu

In 3D Visual Question Answering (3D VQA), the scarcity of fully annotated data and limited visual content diversity hampers the generalization to novel scenes and 3D concepts (e. g., only around 800 scenes are utilized in ScanQA and SQA dataset).

3D Question Answering (3D-QA) Question Answering +1

DEEM: Dynamic Experienced Expert Modeling for Stance Detection

no code implementations23 Feb 2024 Xiaolong Wang, Yile Wang, Sijie Cheng, Peng Li, Yang Liu

Recent work has made a preliminary attempt to use large language models (LLMs) to solve the stance detection task, showing promising results.

Stance Detection

MVD$^2$: Efficient Multiview 3D Reconstruction for Multiview Diffusion

no code implementations22 Feb 2024 Xin-Yang Zheng, Hao Pan, Yu-Xiao Guo, Xin Tong, Yang Liu

By finetuning pretrained large image diffusion models with 3D data, the MVD methods first generate multiple views of a 3D object based on an image or text prompt and then reconstruct 3D shapes with multiview 3D reconstruction.

3D Reconstruction

Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understanding

1 code implementation22 Feb 2024 Yu-Qi Yang, Yu-Xiao Guo, Yang Liu

Data diversity and abundance are essential for improving the performance and generalization of models in natural language processing and 2D vision.

Scene Understanding

OMGEval: An Open Multilingual Generative Evaluation Benchmark for Large Language Models

no code implementations21 Feb 2024 Meng Xu, Shuo Wang, Liner Yang, Haoyu Wang, Zhenghao Liu, Cunliang Kong, Yun Chen, Yang Liu, Maosong Sun, Erhong Yang

We evaluate several representative multilingual LLMs on the proposed OMGEval, which we believe will provide a valuable reference for the community to further understand and improve the multilingual capability of LLMs.

General Knowledge Logical Reasoning

Full-Atom Peptide Design with Geometric Latent Diffusion

no code implementations21 Feb 2024 Xiangzhe Kong, Wenbing Huang, Yang Liu

Peptide design plays a pivotal role in therapeutics, allowing brand new possibility to leverage target binding sites that are previously undruggable.

BMLP: Behavior-aware MLP for Heterogeneous Sequential Recommendation

no code implementations20 Feb 2024 Weixin Li, Yuhao Wu, Yang Liu, Weike Pan, Zhong Ming

In real recommendation scenarios, users often have different types of behaviors, such as clicking and buying.

Sequential Recommendation

Model Composition for Multimodal Large Language Models

no code implementations20 Feb 2024 Chi Chen, Yiyang Du, Zheng Fang, Ziyue Wang, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu

In this paper, we propose a new paradigm through the model composition of existing MLLMs to create a new model that retains the modal understanding capabilities of each original model.

Fair Classifiers Without Fair Training: An Influence-Guided Data Sampling Approach

no code implementations20 Feb 2024 Jinlong Pang, Jialu Wang, Zhaowei Zhu, Yuanshun Yao, Chen Qian, Yang Liu

A fair classifier should ensure the benefit of people from different groups, while the group information is often sensitive and unsuitable for model training.

Attribute Fairness

PANDA: Preference Adaptation for Enhancing Domain-Specific Abilities of LLMs

no code implementations20 Feb 2024 An Liu, Zonghan Yang, Zhenhe Zhang, Qingyuan Hu, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

While Large language models (LLMs) have demonstrated considerable capabilities across various natural language tasks, they often fall short of the performance achieved by domain-specific state-of-the-art models.

text-classification Text Classification

Meta Ranking: Less Capable Language Models are Capable for Single Response Judgement

1 code implementation19 Feb 2024 Zijun Liu, Boqun Kou, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

Although Large Language Models (LLMs) have demonstrated strong performance on a wide range of tasks, they still face reliability challenges such as hallucination.

Hallucination

Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One

no code implementations19 Feb 2024 Tianlin Li, XiaoYu Zhang, Chao Du, Tianyu Pang, Qian Liu, Qing Guo, Chao Shen, Yang Liu

Building on this insight and observation, we develop FairThinking, a pipeline designed to automatically generate roles that enable LLMs to articulate diverse perspectives for fair expressions.

Fairness Language Modelling +1

Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models

1 code implementation19 Feb 2024 Xuanyu Lei, Zonghan Yang, Xinrui Chen, Peng Li, Yang Liu

State-of-the-art Large Multi-Modal Models (LMMs) have demonstrated exceptional capabilities in vision-language tasks.

Visual Prompting

Purifying Large Language Models by Ensembling a Small Language Model

no code implementations19 Feb 2024 Tianlin Li, Qian Liu, Tianyu Pang, Chao Du, Qing Guo, Yang Liu, Min Lin

The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources.

Data Poisoning Language Modelling

Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion

no code implementations19 Feb 2024 Ziyue Wang, Chi Chen, Yiqi Zhu, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu

With the bloom of Large Language Models (LLMs), Multimodal Large Language Models (MLLMs) that incorporate LLMs with pre-trained vision models have recently demonstrated impressive performance across diverse vision-language tasks.

Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages

1 code implementation19 Feb 2024 Yuanchi Zhang, Yile Wang, Zijun Liu, Shuo Wang, Xiaolong Wang, Peng Li, Maosong Sun, Yang Liu

While large language models (LLMs) have been pre-trained on multilingual corpora, their performance still lags behind in most languages compared to a few resource-rich languages.

Transfer Learning

Adversarial Curriculum Graph Contrastive Learning with Pair-wise Augmentation

no code implementations16 Feb 2024 Xinjian Zhao, Liang Zhang, Yang Liu, Ruocheng Guo, Xiangyu Zhao

To address this challenge, we propose an innovative framework: Adversarial Curriculum Graph Contrastive Learning (ACGCL), which capitalizes on the merits of pair-wise augmentation to engender graph-level positive and negative samples with controllable similarity, alongside subgraph contrastive learning to discern effective graph patterns therein.

Contrastive Learning Graph Representation Learning

Measuring and Reducing LLM Hallucination without Gold-Standard Answers via Expertise-Weighting

no code implementations16 Feb 2024 Jiaheng Wei, Yuanshun Yao, Jean-Francois Ton, Hongyi Guo, Andrew Estornell, Yang Liu

In this work, we propose Factualness Evaluations via Weighting LLMs (FEWL), the first hallucination metric that is specifically designed for the scenario when gold-standard answers are absent.

Hallucination In-Context Learning

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues

no code implementations14 Feb 2024 Zhiyuan Chang, Mingyang Li, Yi Liu, Junjie Wang, Qing Wang, Yang Liu

With the development of LLMs, the security threats of LLMs are getting more and more attention.

Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection

1 code implementation14 Feb 2024 Yang Liu, Tongfei Shen, Dong Zhang, Qingying Sun, Shoushan Li, Guodong Zhou

The growing importance of multi-modal humor detection within affective computing correlates with the expanding influence of short-form video sharing on social media platforms.

Humor Detection

Switch EMA: A Free Lunch for Better Flatness and Sharpness

2 code implementations14 Feb 2024 Siyuan Li, Zicheng Liu, Juanxi Tian, Ge Wang, Zedong Wang, Weiyang Jin, Di wu, Cheng Tan, Tao Lin, Yang Liu, Baigui Sun, Stan Z. Li

Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DNN) optimization.

Attribute Image Classification +7

Large Language Models as Agents in Two-Player Games

no code implementations12 Feb 2024 Yang Liu, Peng Sun, Hang Li

By formally defining the training processes of large language models (LLMs), which usually encompasses pre-training, supervised fine-tuning, and reinforcement learning with human feedback, within a single and unified machine learning paradigm, we can glean pivotal insights for advancing LLM technologies.

Position reinforcement-learning

Towards Unified Alignment Between Agents, Humans, and Environment

no code implementations12 Feb 2024 Zonghan Yang, An Liu, Zijun Liu, Kaiming Liu, Fangzhou Xiong, Yile Wang, Zeyuan Yang, Qingyuan Hu, Xinrui Chen, Zhenhe Zhang, Fuwen Luo, Zhicheng Guo, Peng Li, Yang Liu

We also conduct proof-of-concept studies by introducing realistic features to WebShop, including user profiles to demonstrate intentions, personalized reranking for complex environmental dynamics, and runtime cost statistics to reflect self-constraints.

Decision Making

Sparse Anatomical Prompt Semi-Supervised Learning with Masked Image Modeling for CBCT Tooth Segmentation

no code implementations7 Feb 2024 Pengyu Dai, Yafei Ou, Yang Liu, Yue Zhao

To address these challenges, this study aims to propose a tasked-oriented Masked Auto-Encoder paradigm to effectively utilize large amounts of unlabeled data to achieve accurate tooth segmentation with limited labeled data.

Graph Attention Segmentation

FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distribution

no code implementations6 Feb 2024 Qi Zhou, Dongxia Wang, Tianlin Li, Zhihong Xu, Yang Liu, Kui Ren, Wenhai Wang, Qing Guo

To expose this potential vulnerability, we aim to build an adversarial attack forcing SDEdit to generate a specific data distribution aligned with a specified attribute (e. g., female), without changing the input's attribute characteristics.

Adversarial Attack Attribute +1

Space Group Constrained Crystal Generation

no code implementations6 Feb 2024 Rui Jiao, Wenbing Huang, Yu Liu, Deli Zhao, Yang Liu

Crystals are the foundation of numerous scientific and industrial applications.

Weakly Supervised Anomaly Detection via Knowledge-Data Alignment

no code implementations6 Feb 2024 Haihong Zhao, Chenyi Zi, Yang Liu, Chen Zhang, Yan Zhou, Jia Li

In this paper, we introduce a novel framework Knowledge-Data Alignment (KDAlign) to integrate rule knowledge, typically summarized by human experts, to supplement the limited labeled data.

Malware Detection Supervised Anomaly Detection +1

MQuinE: a cure for "Z-paradox" in knowledge graph embedding models

no code implementations5 Feb 2024 Yang Liu, Huang Fang, Yunfeng Cai, Mingming Sun

Knowledge graph embedding (KGE) models achieved state-of-the-art results on many knowledge graph tasks including link prediction and information retrieval.

Information Retrieval Knowledge Graph Embedding +3

Cheating Suffix: Targeted Attack to Text-To-Image Diffusion Models with Multi-Modal Priors

1 code implementation2 Feb 2024 Dingcheng Yang, Yang Bai, Xiaojun Jia, Yang Liu, Xiaochun Cao, Wenjian Yu

The MMP-Attack shows a notable advantage over existing works with superior universality and transferability, which can effectively attack commercial text-to-image (T2I) models such as DALL-E 3.

Image Generation

Graph Neural Networks in EEG-based Emotion Recognition: A Survey

no code implementations2 Feb 2024 Chenyu Liu, Xinliang Zhou, Yihao Wu, Ruizhi Yang, Liming Zhai, Ziyu Jia, Yang Liu

Besides, there is neither a comprehensive review nor guidance for constructing GNNs in EEG-based emotion recognition.

EEG Emotion Recognition +2

Multimodal Embodied Interactive Agent for Cafe Scene

no code implementations1 Feb 2024 Yang Liu, Xinshuai Song, Kaixuan Jiang, Weixing Chen, Jingzhou Luo, Guanbin Li, Liang Lin

To overcome this limitation, we introduce the Multimodal Embodied Interactive Agent (MEIA), capable of translating high-level tasks expressed in natural language into a sequence of executable actions.

Zero-Shot Learning

Node Flux-Linkage Synchronizing Control of Power Systems with 100% Wind Power Generation Based on Capacitor Voltage Balancing Scheme

no code implementations30 Jan 2024 Yang Liu, Yanshan Chen, Yuexi Yang, Xiangyu Pei, Feng Ji

In order to limit the short-circuit current of inverters, a logic-based bang-bang funnel control (LBFC) is designed to control the switches of inverter bridges when over-current is detected.

A Cross-Language Investigation into Jailbreak Attacks in Large Language Models

no code implementations30 Jan 2024 Jie Li, Yi Liu, Chongyang Liu, Ling Shi, Xiaoning Ren, Yaowen Zheng, Yang Liu, Yinxing Xue

To address this research gap, we conducted an extensive empirical study on Multilingual Jailbreak attacks.

Text Generation

A Proactive and Dual Prevention Mechanism against Illegal Song Covers empowered by Singing Voice Conversion

no code implementations30 Jan 2024 Guangke Chen, Yedi Zhang, Fu Song, Ting Wang, Xiaoning Du, Yang Liu

To improve the imperceptibility of perturbations, we refine a psychoacoustic model-based loss with the backing track as an additional masker, a unique accompanying element for singing voices compared to ordinary speech voices.

Voice Conversion

LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning

no code implementations29 Jan 2024 Yuqiang Sun, Daoyuan Wu, Yue Xue, Han Liu, Wei Ma, Lyuye Zhang, Miaolei Shi, Yang Liu

Large language models (LLMs) have demonstrated significant poten- tial for many downstream tasks, including those requiring human- level intelligence, such as vulnerability detection.

Vulnerability Detection

GarchingSim: An Autonomous Driving Simulator with Photorealistic Scenes and Minimalist Workflow

1 code implementation28 Jan 2024 Liguo Zhou, Yinglei Song, Yichao Gao, Zhou Yu, Michael Sodamin, Hongshen Liu, Liang Ma, Lian Liu, Hao liu, Yang Liu, Haichuan Li, Guang Chen, Alois Knoll

However, the availability of free and open-source simulators is limited, and the installation and configuration process can be daunting for beginners and interdisciplinary researchers.

Autonomous Driving

Quantifying Stereotypes in Language

1 code implementation28 Jan 2024 Yang Liu

It is often potentially encoded in human language, which is more common in texts on social issues.

Sentence

SkipViT: Speeding Up Vision Transformers with a Token-Level Skip Connection

no code implementations27 Jan 2024 Foozhan Ataiefard, Walid Ahmed, Habib Hajimolahoseini, Saina Asani, Farnoosh Javadi, Mohammad Hassanpour, Omar Mohamed Awad, Austin Wen, Kangling Liu, Yang Liu

Our method does not add any parameters to the ViT model and aims to find the best trade-off between training throughput and achieving a 0% loss in the Top-1 accuracy of the final model.

Generative Video Diffusion for Unseen Cross-Domain Video Moment Retrieval

no code implementations24 Jan 2024 Dezhao Luo, Shaogang Gong, Jiabo Huang, Hailin Jin, Yang Liu

We address two problems in video editing for optimising unseen domain VMR: (1) generation of high-quality simulation videos of different moments with subtle distinctions, (2) selection of simulation videos that complement existing source training videos without introducing harmful noise or unnecessary repetitions.

Moment Retrieval Retrieval +2

UniHDA: A Unified and Versatile Framework for Multi-Modal Hybrid Domain Adaptation

no code implementations23 Jan 2024 Hengjia Li, Yang Liu, Yuqi Lin, Zhanwei Zhang, Yibo Zhao, weihang Pan, Tu Zheng, Zheng Yang, Yuchun Jiang, Boxi Wu, Deng Cai

In this paper, we propose UniHDA, a \textbf{unified} and \textbf{versatile} framework for generative hybrid domain adaptation with multi-modal references from multiple domains.

Attribute Domain Adaptation

Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models

1 code implementation22 Jan 2024 Yile Wang, Sijie Cheng, Zixin Sun, Peng Li, Yang Liu

We propose symbol-to-language (S2L), a tuning-free method that enables large language models to solve symbol-related problems with information expressed in natural language.

Property Prediction Question Answering +1

Robust Evaluation Measures for Evaluating Social Biases in Masked Language Models

1 code implementation21 Jan 2024 Yang Liu

Many evaluation measures are used to evaluate social biases in masked language models (MLMs).

CBVS: A Large-Scale Chinese Image-Text Benchmark for Real-World Short Video Search Scenarios

1 code implementation19 Jan 2024 Xiangshuo Qiao, Xianxin Li, Xiaozhe Qu, Jie Zhang, Yang Liu, Yu Luo, Cihang Jin, Jin Ma

Differently, video covers in short video search scenarios are presented as user-originated contents that provide important visual summaries of videos.

Common Sense Reasoning Image Retrieval

LLMs for Relational Reasoning: How Far are We?

no code implementations17 Jan 2024 Zhiming Li, Yushi Cao, Xiufeng Xu, Junzhe Jiang, Xu Liu, Yon Shin Teo, Shang-Wei Lin, Yang Liu

Large language models (LLMs) have revolutionized many areas (e. g. natural language processing, software engineering, etc.)

Common Sense Reasoning Decision Making +3

Rigid Protein-Protein Docking via Equivariant Elliptic-Paraboloid Interface Prediction

1 code implementation17 Jan 2024 Ziyang Yu, Wenbing Huang, Yang Liu

The study of rigid protein-protein docking plays an essential role in a variety of tasks such as drug design and protein engineering.

Short-Form Videos and Mental Health: A Knowledge-Guided Multimodal Neural Topic Model

no code implementations11 Jan 2024 Jiaheng Xie, Ruicheng Liang, Yidong Chai, Yang Liu, Daniel Zeng

To prevent widespread consequences, platforms are eager to predict these videos' impact on viewers' mental health.

Topic Models Video Classification

Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security

1 code implementation10 Jan 2024 Yuanchun Li, Hao Wen, Weijun Wang, Xiangyu Li, Yizhen Yuan, Guohong Liu, Jiacheng Liu, Wenxing Xu, Xiang Wang, Yi Sun, Rui Kong, Yile Wang, Hanfei Geng, Jian Luan, Xuefeng Jin, Zilong Ye, Guanjing Xiong, Fan Zhang, Xiang Li, Mengwei Xu, Zhijun Li, Peng Li, Yang Liu, Ya-Qin Zhang, Yunxin Liu

Next, we discuss several key challenges to achieve intelligent, efficient and secure Personal LLM Agents, followed by a comprehensive survey of representative solutions to address these challenges.

FADI-AEC: Fast Score Based Diffusion Model Guided by Far-end Signal for Acoustic Echo Cancellation

no code implementations8 Jan 2024 Yang Liu, Li Wan, Yun Li, Yiteng Huang, Ming Sun, James Luan, Yangyang Shi, Xin Lei

Despite the potential of diffusion models in speech enhancement, their deployment in Acoustic Echo Cancellation (AEC) has been restricted.

Acoustic echo cancellation Speech Enhancement

FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning

3 code implementations6 Jan 2024 Jianqing Zhang, Yang Liu, Yang Hua, Jian Cao

To reduce the high communication cost of transmitting model parameters, a major challenge in HtFL, prototype-based HtFL methods are proposed to solely share class representatives, a. k. a, prototypes, among heterogeneous clients while maintaining the privacy of clients' models.

Contrastive Learning Federated Learning

Human-Instruction-Free LLM Self-Alignment with Limited Samples

no code implementations6 Jan 2024 Hongyi Guo, Yuanshun Yao, Wei Shen, Jiaheng Wei, Xiaoying Zhang, Zhaoran Wang, Yang Liu

The key idea is to first retrieve high-quality samples related to the target domain and use them as In-context Learning examples to generate more samples.

In-Context Learning Instruction Following

Digger: Detecting Copyright Content Mis-usage in Large Language Model Training

no code implementations1 Jan 2024 Haodong Li, Gelei Deng, Yi Liu, Kailong Wang, Yuekang Li, Tianwei Zhang, Yang Liu, Guoai Xu, Guosheng Xu, Haoyu Wang

In this paper, we introduce a detailed framework designed to detect and assess the presence of content from potentially copyrighted books within the training datasets of LLMs.

Language Modelling Large Language Model +1

Masked Modeling for Self-supervised Representation Learning on Vision and Beyond

1 code implementation31 Dec 2023 Siyuan Li, Luyuan Zhang, Zedong Wang, Di wu, Lirong Wu, Zicheng Liu, Jun Xia, Cheng Tan, Yang Liu, Baigui Sun, Stan Z. Li

As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and the low dependence on labeled data.

Representation Learning Self-Supervised Learning

Exploiting Multipath Information for Integrated Localization and Sensing via PHD Filtering

no code implementations24 Dec 2023 Yinuo Du, Hanying Zhao, Yang Liu, Xinlei Yu, Yuan Shen

Accurate localization and perception are pivotal for enhancing the safety and reliability of vehicles.

Multimodal Federated Learning with Missing Modality via Prototype Mask and Contrast

no code implementations21 Dec 2023 Guangyin Bao, Qi Zhang, Duoqian Miao, Zixuan Gong, Liang Hu, Ke Liu, Yang Liu, Chongyang Shi

In real-world scenarios, multimodal federated learning often faces the practical challenge of intricate modality missing, which poses constraints on building federated frameworks and significantly degrades model inference accuracy.

Federated Learning

A Semi-Analytical Approach for State-Space Electromagnetic Transient Simulation Using the Differential Transformation

no code implementations19 Dec 2023 Min Xiong, Kaiyang Huang, Yang Liu, Rui Yao, Kai Sun, Feng Qiu

Case studies are conducted on EMT models of the IEEE 39-bus system and a synthetic 390-bus system to demonstrate the merits of the new simulation approach against traditional methods.

Probabilistic Prediction of Longitudinal Trajectory Considering Driving Heterogeneity with Interpretability

no code implementations19 Dec 2023 Shuli Wang, Kun Gao, Lanfang Zhang, Yang Liu, Lei Chen

Specifically, based on a certain length of historical trajectory data, the situation-specific driving preferences of each driver are identified, where key driving behavior feature vectors are extracted to characterize heterogeneity in driving behavior among different drivers.

Navigate Trajectory Prediction

Mutual Enhancement of Large and Small Language Models with Cross-Silo Knowledge Transfer

no code implementations10 Dec 2023 Yongheng Deng, Ziqing Qiao, Ju Ren, Yang Liu, Yaoxue Zhang

While large language models (LLMs) are empowered with broad knowledge, their task-specific performance is often suboptimal.

Transfer Learning

PFLlib: Personalized Federated Learning Algorithm Library

1 code implementation8 Dec 2023 Jianqing Zhang, Yang Liu, Yang Hua, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, Jian Cao

Amid the ongoing advancements in Federated Learning (FL), a machine learning paradigm that allows collaborative learning with data privacy protection, personalized FL (pFL) has gained significant prominence as a research direction within the FL domain.

Personalized Federated Learning

Detecting and Restoring Non-Standard Hands in Stable Diffusion Generated Images

no code implementations7 Dec 2023 Yiqun Zhang, Zhenyue Qin, Yang Liu, Dylan Campbell

We introduce a pipeline to address anatomical inaccuracies in Stable Diffusion generated hand images.

Pose Estimation

OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization

no code implementations7 Dec 2023 Dongchen Han, Xiaojun Jia, Yang Bai, Jindong Gu, Yang Liu, Xiaochun Cao

Investigating the generation of high-transferability adversarial examples is crucial for uncovering VLP models' vulnerabilities in practical scenarios.

Adversarial Attack Data Augmentation +2

TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation

no code implementations3 Dec 2023 Xiaojun Jia, Jindong Gu, Yihao Huang, Simeng Qin, Qing Guo, Yang Liu, Xiaochun Cao

At the second stage, the pixels are divided into different branches based on their transferable property which is dependent on Kullback-Leibler divergence.

Adversarial Attack Image Classification +2

Abstract Syntax Tree for Programming Language Understanding and Representation: How Far Are We?

1 code implementation1 Dec 2023 Weisong Sun, Chunrong Fang, Yun Miao, Yudu You, Mengzhe Yuan, Yuchen Chen, Quanjun Zhang, An Guo, Xiang Chen, Yang Liu, Zhenyu Chen

To do so, we compare the performance of models trained with code token sequence (Token for short) based code representation and AST-based code representation on three popular types of code-related tasks.

Representation Learning

CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation

no code implementations30 Nov 2023 Zineng Tang, ZiYi Yang, Mahmoud Khademi, Yang Liu, Chenguang Zhu, Mohit Bansal

We present CoDi-2, a versatile and interactive Multimodal Large Language Model (MLLM) that can follow complex multimodal interleaved instructions, conduct in-context learning (ICL), reason, chat, edit, etc., in an any-to-any input-output modality paradigm.

Image Generation In-Context Learning +3

StructRe: Rewriting for Structured Shape Modeling

no code implementations29 Nov 2023 Jiepeng Wang, Hao Pan, Yang Liu, Xin Tong, Taku Komura, Wenping Wang

Such a localized rewriting process enables probabilistic modeling of ambiguous structures and robust generalization across object categories.

Object

Topology-Preserving Adversarial Training

no code implementations29 Nov 2023 Xiaoyue Mi, Fan Tang, Yepeng Weng, Danding Wang, Juan Cao, Sheng Tang, Peng Li, Yang Liu

Despite the effectiveness in improving the robustness of neural networks, adversarial training has suffered from the natural accuracy degradation problem, i. e., accuracy on natural samples has reduced significantly.

Adversarial Robust Memory-Based Continual Learner

no code implementations29 Nov 2023 Xiaoyue Mi, Fan Tang, Zonghan Yang, Danding Wang, Juan Cao, Peng Li, Yang Liu

Despite the remarkable advances that have been made in continual learning, the adversarial vulnerability of such methods has not been fully discussed.

Adversarial Robustness Continual Learning

Q-learning Based Optimal False Data Injection Attack on Probabilistic Boolean Control Networks

no code implementations29 Nov 2023 Xianlun Peng, Yang Tang, Fangfei Li, Yang Liu

In this paper, we present a reinforcement learning (RL) method for solving optimal false data injection attack problems in probabilistic Boolean control networks (PBCNs) where the attacker lacks knowledge of the system model.

Q-Learning reinforcement-learning +1

Animatable 3D Gaussian: Fast and High-Quality Reconstruction of Multiple Human Avatars

1 code implementation27 Nov 2023 Yang Liu, Xiang Huang, Minghan Qin, Qinwei Lin, Haoqian Wang

Neural radiance fields are capable of reconstructing high-quality drivable human avatars but are expensive to train and render.

Novel View Synthesis

Can Vision-Language Models Think from a First-Person Perspective?

1 code implementation27 Nov 2023 Sijie Cheng, Zhicheng Guo, Jingwen Wu, Kechen Fang, Peng Li, Huaping Liu, Yang Liu

However, the capability of VLMs to "think" from a first-person perspective, a crucial attribute for advancing autonomous agents and robotics, remains largely unexplored.

Attribute Question Answering +1

SwiftLearn: A Data-Efficient Training Method of Deep Learning Models using Importance Sampling

no code implementations25 Nov 2023 Habib Hajimolahoseini, Omar Mohamed Awad, Walid Ahmed, Austin Wen, Saina Asani, Mohammad Hassanpour, Farnoosh Javadi, Mehdi Ahmadi, Foozhan Ataiefard, Kangling Liu, Yang Liu

In this paper, we present SwiftLearn, a data-efficient approach to accelerate training of deep learning models using a subset of data samples selected during the warm-up stages of training.

Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language

no code implementations24 Nov 2023 Di Jin, Shikib Mehri, Devamanyu Hazarika, Aishwarya Padmakumar, Sungjin Lee, Yang Liu, Mahdi Namazifar

Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations.

AdapterFL: Adaptive Heterogeneous Federated Learning for Resource-constrained Mobile Computing Systems

no code implementations23 Nov 2023 Ruixuan Liu, Ming Hu, Zeke Xia, Jun Xia, Pengyu Zhang, Yihao Huang, Yang Liu, Mingsong Chen

On the one hand, to achieve model training in all the diverse clients, mobile computing systems can only use small low-performance models for collaborative learning.

Federated Learning

AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systems

no code implementations22 Nov 2023 Chentao Jia, Ming Hu, Zekai Chen, Yanxin Yang, Xiaofei Xie, Yang Liu, Mingsong Chen

Although Federated Learning (FL) is promising to enable collaborative learning among Artificial Intelligence of Things (AIoT) devices, it suffers from the problem of low classification performance due to various heterogeneity factors (e. g., computing capacity, memory size) of devices and uncertain operating environments.

Federated Learning

Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions

1 code implementation20 Nov 2023 Ziyue Wang, Chi Chen, Peng Li, Yang Liu

Large Language Models (LLMs) demonstrate impressive reasoning ability and the maintenance of world knowledge not only in natural language tasks, but also in some vision-language tasks such as open-domain knowledge-based visual question answering (OK-VQA).

Question Answering Visual Question Answering +1

A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems

1 code implementation Scientific Reports 2023 Shuo Zhang, Yang Liu, Lei Xie

Molecular sciences address a wide range of problems involving molecules of different types and sizes and their complexes.

Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models

1 code implementation19 Nov 2023 Zhaowei Zhu, Jialu Wang, Hao Cheng, Yang Liu

Given the cost and difficulty of cleaning these datasets by humans, we introduce a systematic framework for evaluating the credibility of datasets, identifying label errors, and evaluating the influence of noisy labels in the curated language data, specifically focusing on unsafe comments and conversation classification.

Language Modelling

AI-accelerated Discovery of Altermagnetic Materials

1 code implementation8 Nov 2023 Ze-Feng Gao, Shuai Qu, Bocheng Zeng, Yang Liu, Ji-Rong Wen, Hao Sun, Peng-Jie Guo, Zhong-Yi Lu

Altermagnetism, a new magnetic phase, has been theoretically proposed and experimentally verified to be distinct from ferromagnetism and antiferromagnetism.

Lagrangian Modelling and Motion Stability of Synchronous Generator Power Systems

no code implementations7 Nov 2023 Feng Ji, Lu Gao, Chang Lin, Yang Liu

This paper proposes to analyze the motion stability of synchro-nous generator power systems using a Lagrangian model derived in the configuration space of generalized position and speed.

GQKVA: Efficient Pre-training of Transformers by Grouping Queries, Keys, and Values

no code implementations6 Nov 2023 Farnoosh Javadi, Walid Ahmed, Habib Hajimolahoseini, Foozhan Ataiefard, Mohammad Hassanpour, Saina Asani, Austin Wen, Omar Mohamed Awad, Kangling Liu, Yang Liu

We tested our method on ViT, which achieved an approximate 0. 3% increase in accuracy while reducing the model size by about 4% in the task of image classification.

Image Classification

Procedural Fairness Through Decoupling Objectionable Data Generating Components

1 code implementation5 Nov 2023 Zeyu Tang, Jialu Wang, Yang Liu, Peter Spirtes, Kun Zhang

We reveal and address the frequently overlooked yet important issue of disguised procedural unfairness, namely, the potentially inadvertent alterations on the behavior of neutral (i. e., not problematic) aspects of data generating process, and/or the lack of procedural assurance of the greatest benefit of the least advantaged individuals.

Decision Making Fairness

Few-shot Hybrid Domain Adaptation of Image Generators

1 code implementation30 Oct 2023 Hengjia Li, Yang Liu, Linxuan Xia, Yuqi Lin, Tu Zheng, Zheng Yang, Wenxiao Wang, Xiaohui Zhong, Xiaobo Ren, Xiaofei He

Concretely, the distance loss blends the attributes of all target domains by reducing the distances from generated images to all target subspaces.

Domain Adaptation Semantic Similarity +1

Sentence Bag Graph Formulation for Biomedical Distant Supervision Relation Extraction

no code implementations29 Oct 2023 Hao Zhang, Yang Liu, Xiaoyan Liu, Tianming Liang, Gaurav Sharma, Liang Xue, Maozu Guo

We introduce a novel graph-based framework for alleviating key challenges in distantly-supervised relation extraction and demonstrate its effectiveness in the challenging and important domain of biomedical data.

Relation Relation Extraction +1

The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions

1 code implementation19 Oct 2023 Siru Ouyang, Shuohang Wang, Yang Liu, Ming Zhong, Yizhu Jiao, Dan Iter, Reid Pryzant, Chenguang Zhu, Heng Ji, Jiawei Han

Recent progress in Large Language Models (LLMs) has produced models that exhibit remarkable performance across a variety of NLP tasks.

Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models

no code implementations19 Oct 2023 Zhihan Zhang, Shuohang Wang, Wenhao Yu, Yichong Xu, Dan Iter, Qingkai Zeng, Yang Liu, Chenguang Zhu, Meng Jiang

Large language models (LLMs) can perform a wide range of tasks by following natural language instructions, without the necessity of task-specific fine-tuning.

IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks

no code implementations18 Oct 2023 Yue Cao, Tianlin Li, Xiaofeng Cao, Ivor Tsang, Yang Liu, Qing Guo

The underlying rationale behind our idea is that image resampling can alleviate the influence of adversarial perturbations while preserving essential semantic information, thereby conferring an inherent advantage in defending against adversarial attacks.

Adversarial Robustness

A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis

1 code implementation18 Oct 2023 Shuhan Zhong, Sizhe Song, Guanyao Li, Weipeng Zhuo, Yang Liu, S. -H. Gary Chan

Time series data, often characterized by unique composition and complex multi-scale temporal variations, requires special consideration of decomposition and multi-scale modeling in its analysis.

Anomaly Detection Imputation +2

Co-Learning Semantic-aware Unsupervised Segmentation for Pathological Image Registration

no code implementations17 Oct 2023 Yang Liu, Shi Gu

Our results show that our method can accurately achieve the registration of pathological images and identify lesions even in challenging imaging modalities.

Image Registration Segmentation

VFLAIR: A Research Library and Benchmark for Vertical Federated Learning

1 code implementation15 Oct 2023 Tianyuan Zou, Zixuan Gu, Yu He, Hideaki Takahashi, Yang Liu, Guangnan Ye, Ya-Qin Zhang

Vertical Federated Learning (VFL) has emerged as a collaborative training paradigm that allows participants with different features of the same group of users to accomplish cooperative training without exposing their raw data or model parameters.

Vertical Federated Learning

Large Language Model Unlearning

1 code implementation14 Oct 2023 Yuanshun Yao, Xiaojun Xu, Yang Liu

To the best of our knowledge, our work is among the first to explore LLM unlearning.

Language Modelling Large Language Model

Graph Condensation via Eigenbasis Matching

no code implementations13 Oct 2023 Yang Liu, Deyu Bo, Chuan Shi

The increasing amount of graph data places requirements on the efficiency and scalability of graph neural networks (GNNs), despite their effectiveness in various graph-related applications.

Fair Classifiers that Abstain without Harm

no code implementations9 Oct 2023 Tongxin Yin, Jean-François Ton, Ruocheng Guo, Yuanshun Yao, Mingyan Liu, Yang Liu

To generalize the abstaining decisions to test samples, we then train a surrogate model to learn the abstaining decisions based on the IP solutions in an end-to-end manner.

Decision Making Fairness

Logic-guided Deep Reinforcement Learning for Stock Trading

no code implementations9 Oct 2023 Zhiming Li, Junzhe Jiang, Yushi Cao, Aixin Cui, Bozhi Wu, Bo Li, Yang Liu

In this paper, we propose a novel logic-guided trading framework, termed as SYENS (Program Synthesis-based Ensemble Strategy).

Program Synthesis reinforcement-learning

CCAE: A Corpus of Chinese-based Asian Englishes

no code implementations9 Oct 2023 Yang Liu, Melissa Xiaohui Qin, Long Wang, Chao Huang

The ontology of data would make the corpus a helpful resource with enormous research potential for Asian Englishes (especially for Chinese Englishes for which there has not been a publicly accessible corpus yet so far) and an ideal source for variety-specific language modeling and downstream tasks, thus setting the stage for NLP-based World Englishes studies.

Language Modelling

Post-hoc Bias Scoring Is Optimal For Fair Classification

1 code implementation9 Oct 2023 Wenlong Chen, Yegor Klochkov, Yang Liu

We consider a binary classification problem under group fairness constraints, which can be one of Demographic Parity (DP), Equalized Opportunity (EOp), or Equalized Odds (EO).

Binary Classification Fairness

Deep Concept Removal

no code implementations9 Oct 2023 Yegor Klochkov, Jean-Francois Ton, Ruocheng Guo, Yang Liu, Hang Li

We address the problem of concept removal in deep neural networks, aiming to learn representations that do not encode certain specified concepts (e. g., gender etc.)

Attribute Out-of-Distribution Generalization

Self-Knowledge Guided Retrieval Augmentation for Large Language Models

no code implementations8 Oct 2023 Yile Wang, Peng Li, Maosong Sun, Yang Liu

Large language models (LLMs) have shown superior performance without task-specific fine-tuning.

Question Answering Retrieval +1

Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization

1 code implementation3 Oct 2023 Zijun Liu, Yanzhe Zhang, Peng Li, Yang Liu, Diyi Yang

We further design an automatic agent team optimization algorithm based on an unsupervised metric termed $\textit{Agent Importance Score}$, enabling the selection of best agents based on the contribution each agent makes.

Code Generation Language Modelling +2

Split and Merge: Aligning Position Biases in Large Language Model based Evaluators

no code implementations29 Sep 2023 Zongjie Li, Chaozheng Wang, Pingchuan Ma, Daoyuan Wu, Shuai Wang, Cuiyun Gao, Yang Liu

Specifically, PORTIA splits the answers into multiple segments, aligns similar content across candidate answers, and then merges them back into a single prompt for evaluation by LLMs.

Language Modelling Large Language Model +1

Learning Effective NeRFs and SDFs Representations with 3D Generative Adversarial Networks for 3D Object Generation: Technical Report for ICCV 2023 OmniObject3D Challenge

no code implementations28 Sep 2023 Zheyuan Yang, Yibo Liu, Guile Wu, Tongtong Cao, Yuan Ren, Yang Liu, Bingbing Liu

To resolve this problem, we study learning effective NeRFs and SDFs representations with 3D Generative Adversarial Networks (GANs) for 3D object generation.

Object

Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning

1 code implementation25 Sep 2023 Yang Liu, Chen Chen, Can Wang, Xulin King, Mengyuan Liu

The proposed method decouples functions between the decoder and the encoder by introducing a mask regressor, which predicts the masked patch representation from the visible patch representation encoded by the encoder and the decoder reconstructs the target from the predicted masked patch representation.

Few-Shot 3D Point Cloud Classification Representation Learning +1

Speeding up Resnet Architecture with Layers Targeted Low Rank Decomposition

no code implementations21 Sep 2023 Walid Ahmed, Habib Hajimolahoseini, Austin Wen, Yang Liu

Compression of a neural network can help in speeding up both the training and the inference of the network.

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

1 code implementation20 Sep 2023 Guan Wang, Sijie Cheng, Xianyuan Zhan, Xiangang Li, Sen Song, Yang Liu

Specifically, we consider the general SFT training data, consisting of a small amount of expert data mixed with a large proportion of sub-optimal data, without any preference labels.

Arithmetic Reasoning Code Generation +1

An Empirical Study of Attention Networks for Semantic Segmentation

no code implementations19 Sep 2023 Hao Guo, Hongbiao Si, Guilin Jiang, Wei zhang, Zhiyan Liu, Xuanyi Zhu, xulong Zhang, Yang Liu

What's more, various methods utilize attention in semantic segmentation, but the conclusion of these methods is lacking.

Segmentation Semantic Segmentation

GAME: Generalized deep learning model towards multimodal data integration for early screening of adolescent mental disorders

no code implementations18 Sep 2023 Zhicheng Du, Chenyao Jiang, Xi Yuan, Shiyao Zhai, Zhengyang Lei, Shuyue Ma, Yang Liu, Qihui Ye, Chufan Xiao, Qiming Huang, Ming Xu, Dongmei Yu, Peiwu Qin

The timely identification of mental disorders in adolescents is a global public health challenge. Single factor is difficult to detect the abnormality due to its complex and subtle nature.

Data Integration

Distributionally Robust Post-hoc Classifiers under Prior Shifts

1 code implementation16 Sep 2023 Jiaheng Wei, Harikrishna Narasimhan, Ehsan Amid, Wen-Sheng Chu, Yang Liu, Abhishek Kumar

We investigate the problem of training models that are robust to shifts caused by changes in the distribution of class-priors or group-priors.

Enhance audio generation controllability through representation similarity regularization

no code implementations15 Sep 2023 Yangyang Shi, Gael Le Lan, Varun Nagaraja, Zhaoheng Ni, Xinhao Mei, Ernie Chang, Forrest Iandola, Yang Liu, Vikas Chandra

This paper presents an innovative approach to enhance control over audio generation by emphasizing the alignment between audio and text representations during model training.

Audio Generation Language Modelling +2

Federated PAC-Bayesian Learning on Non-IID data

no code implementations13 Sep 2023 Zihao Zhao, Yang Liu, Wenbo Ding, Xiao-Ping Zhang

Existing research has either adapted the Probably Approximately Correct (PAC) Bayesian framework for federated learning (FL) or used information-theoretic PAC-Bayesian bounds while introducing their theorems, but few considering the non-IID challenges in FL.

Federated Learning

Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf

no code implementations9 Sep 2023 Yuzhuang Xu, Shuo Wang, Peng Li, Fuwen Luo, Xiaolong Wang, Weidong Liu, Yang Liu

Communication games, which we refer to as incomplete information games that heavily depend on natural language communication, hold significant research value in fields such as economics, social science, and artificial intelligence.

Retrieval

Improving Resnet-9 Generalization Trained on Small Datasets

no code implementations7 Sep 2023 Omar Mohamed Awad, Habib Hajimolahoseini, Michael Lim, Gurpreet Gosal, Walid Ahmed, Yang Liu, Gordon Deng

This paper presents our proposed approach that won the first prize at the ICLR competition on Hardware Aware Efficient Training.

Image Classification

Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory

1 code implementation ICCV 2023 Ting Lei, Fabian Caba, Qingchao Chen, Hailin Jin, Yuxin Peng, Yang Liu

This observation motivates us to design an HOI detector that can be trained even with long-tailed labeled data and can leverage existing knowledge from pre-trained models.

Human-Object Interaction Detection Retrieval

Training Acceleration of Low-Rank Decomposed Networks using Sequential Freezing and Rank Quantization

no code implementations7 Sep 2023 Habib Hajimolahoseini, Walid Ahmed, Yang Liu

Low Rank Decomposition (LRD) is a model compression technique applied to the weight tensors of deep learning models in order to reduce the number of trainable parameters and computational complexity.

Model Compression Quantization

Adaptive Adversarial Training Does Not Increase Recourse Costs

no code implementations5 Sep 2023 Ian Hardy, Jayanth Yetukuri, Yang Liu

Recent work has connected adversarial attack methods and algorithmic recourse methods: both seek minimal changes to an input instance which alter a model's classification decision.

Adversarial Attack

Towards User Guided Actionable Recourse

no code implementations5 Sep 2023 Jayanth Yetukuri, Ian Hardy, Yang Liu

Machine Learning's proliferation in critical fields such as healthcare, banking, and criminal justice has motivated the creation of tools which ensure trust and transparency in ML models.

Bayesian estimation and reconstruction of marine surface contaminant dispersion

no code implementations1 Sep 2023 Yang Liu, Christopher M. Harvey, Frederick E. Hamlyn, Cunjia Liu

The PDE model is spatially discretised into a linear state-space model using the dynamic transient finite-element method (FEM) so that the characterisation of time-varying dispersion can be cast into the problem of inferring the model states from sensor measurements.

Prompt-enhanced Hierarchical Transformer Elevating Cardiopulmonary Resuscitation Instruction via Temporal Action Segmentation

no code implementations31 Aug 2023 Yang Liu, Xiaoyun Zhong, Shiyao Zhai, Zhicheng Du, Zhenyuan Gao, Qiming Huang, Canyang Zhang, Bin Jiang, Vijay Kumar Pandey, Sanyang Han, Runming Wang, Yuxing Han, Peiwu Qin

The vast majority of people who suffer unexpected cardiac arrest are performed cardiopulmonary resuscitation (CPR) by passersby in a desperate attempt to restore life, but endeavors turn out to be fruitless on account of disqualification.

Action Segmentation Segmentation

Masked Transformer for Electrocardiogram Classification

no code implementations31 Aug 2023 Ya Zhou, Xiaolin Diao, Yanni Huo, Yang Liu, Xiaohan Fan, Wei Zhao

We construct a dataset comprising 220, 251 ECG recordings with a broad range of diagnoses annoated by medical experts to explore the properties of MTECG.

Classification ECG Classification +1

FaceChain: A Playground for Human-centric Artificial Intelligence Generated Content

1 code implementation28 Aug 2023 Yang Liu, Cheng Yu, Lei Shang, Yongyi He, Ziheng Wu, Xingjun Wang, Chao Xu, Haoyu Xie, Weida Wang, Yuze Zhao, Lin Zhu, Chen Cheng, Weitao Chen, Yuan YAO, Wenmeng Zhou, Jiaqi Xu, Qiang Wang, Yingda Chen, Xuansong Xie, Baigui Sun

In this paper, we present FaceChain, a personalized portrait generation framework that combines a series of customized image-generation model and a rich set of face-related perceptual understanding models (\eg, face detection, deep face embedding extraction, and facial attribute recognition), to tackle aforementioned challenges and to generate truthful personalized portraits, with only a handful of portrait images as input.

Attribute Potrait Generation +1

Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models

1 code implementation25 Aug 2023 Chi Chen, Ruoyu Qin, Fuwen Luo, Xiaoyue Mi, Peng Li, Maosong Sun, Yang Liu

However, existing visual instruction tuning methods only utilize image-language instruction data to align the language and image modalities, lacking a more fine-grained cross-modal alignment.

Position

SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases

no code implementations25 Aug 2023 Yang Liu, Jiashun Cheng, Haihong Zhao, Tingyang Xu, Peilin Zhao, Fugee Tsung, Jia Li, Yu Rong

Furthermore, we offer theoretical insights into SEGNO, highlighting that it can learn a unique trajectory between adjacent states, which is crucial for model generalization.

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