Search Results for author: Yi Zhang

Found 362 papers, 119 papers with code

Translation as Cross-Domain Knowledge: Attention Augmentation for Unsupervised Cross-Domain Segmenting and Labeling Tasks

1 code implementation Findings (EMNLP) 2021 Ruixuan Luo, Yi Zhang, Sishuo Chen, Xu sun

The nature of no word delimiter or inflection that can indicate segment boundaries or word semantics increases the difficulty of Chinese text understanding, and also intensifies the demand for word-level semantic knowledge to accomplish the tagging goal in Chinese segmenting and labeling tasks.


ODIST: Open World Classification via Distributionally Shifted Instances

no code implementations Findings (EMNLP) 2021 Lei Shu, Yassine Benajiba, Saab Mansour, Yi Zhang

In this work, we address the open-world classification problem with a method called ODIST, open world classification via distributionally shifted instances.

Classification Language Modelling

PCA-Relax: Deep-learning-based groupwise registration for motion correction of cardiac $T_1$ mapping

no code implementations18 Jun 2024 Yi Zhang, Yidong Zhao, Lu Huang, Liming Xia, Qian Tao

In this work, we propose a novel deep-learning-based groupwise registration framework, which omits the need for a template, and registers all baseline images simultaneously.

TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy

1 code implementation17 Jun 2024 Yiqun Chen, Qi Liu, Yi Zhang, Weiwei Sun, Daiting Shi, Jiaxin Mao, Dawei Yin

However, several significant challenges still persist in LLMs for ranking: (1) LLMs are constrained by limited input length, precluding them from processing a large number of documents simultaneously; (2) The output document sequence is influenced by the input order of documents, resulting in inconsistent ranking outcomes; (3) Achieving a balance between cost and ranking performance is quite challenging.

MDCR: A Dataset for Multi-Document Conditional Reasoning

no code implementations17 Jun 2024 Peter Baile Chen, Yi Zhang, Chunwei Liu, Sejal Gupta, Yoon Kim, Michael Cafarella

For instance, whether a student is eligible for a scholarship depends on eligibility conditions, such as major or degree required.

DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data

1 code implementation CVPR 2024 Qihao Liu, Yi Zhang, Song Bai, Adam Kortylewski, Alan Yuille

Unlike recent 3D generative models that rely on clean and well-aligned 3D data, limiting them to single or few-class generation, our model is directly trained on extensive noisy and unaligned `in-the-wild' 3D assets, mitigating the key challenge (i. e., data scarcity) in large-scale 3D generation.

3D Generation Text to 3D

StatBot.Swiss: Bilingual Open Data Exploration in Natural Language

no code implementations5 Jun 2024 Farhad Nooralahzadeh, Yi Zhang, Ellery Smith, Sabine Maennel, Cyril Matthey-Doret, Raphaël de Fondville, Kurt Stockinger

The potential for improvements brought by Large Language Models (LLMs) in Text-to-SQL systems is mostly assessed on monolingual English datasets.

In-Context Learning Text-To-SQL

Programmable Multi-input Buck-Boost Converter for Photovoltaics Arrays

no code implementations3 Jun 2024 Zhongting Tang, Yi Zhang, Pooya Davari

This paper proposes a programmable multi-input buck-boost structure method, which can enhance the operation tolerance for the PV array under extremely harsh climatic conditions.

A re-calibration method for object detection with multi-modal alignment bias in autonomous driving

no code implementations27 May 2024 Zhihang Song, Lihui Peng, Jianming Hu, Danya Yao, Yi Zhang

As the research on the calibration influence on fusion detection performance is relatively few, flexible calibration dependency multi-sensor detection method has always been attractive.

Autonomous Driving object-detection +2

Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference

no code implementations26 May 2024 Xunpeng Huang, Difan Zou, Hanze Dong, Yi Zhang, Yi-An Ma, Tong Zhang

To generate data from trained diffusion models, most inference algorithms, such as DDPM, DDIM, and other variants, rely on discretizing the reverse SDEs or their equivalent ODEs.


Small Language Models for Application Interactions: A Case Study

no code implementations23 May 2024 Beibin Li, Yi Zhang, Sébastien Bubeck, Jeevan Pathuri, Ishai Menache

We study the efficacy of Small Language Models (SLMs) in facilitating application usage through natural language interactions.

ECLIPSE: Semantic Entropy-LCS for Cross-Lingual Industrial Log Parsing

no code implementations22 May 2024 Wei zhang, Xianfu Cheng, Yi Zhang, Jian Yang, Hongcheng Guo, Zhoujun Li, Xiaolin Yin, Xiangyuan Guan, Xu Shi, Liangfan Zheng, Bo Zhang

These challenges are two-fold: 1) massive log templates: The performance and efficiency of most existing parsers will be significantly reduced when logs of growing quantities and different lengths; 2) Complex and changeable semantics: Traditional template-matching algorithms cannot accurately match the log templates of complicated industrial logs because they cannot utilize cross-language logs with similar semantics.

Language Modelling Large Language Model +2

Adaptive Optimal Market Making Strategies with Inventory Liquidation Cos

no code implementations19 May 2024 Jonathan Chávez-Casillas, José E. Figueroa-López, Chuyi Yu, Yi Zhang

A novel high-frequency market-making approach in discrete time is proposed that admits closed-form solutions.

Ptychographic non-line-of-sight imaging for depth-resolved visualization of hidden objects

no code implementations17 May 2024 Pengming Song, Qianhao Zhao, Ruihai Wang, Ninghe Liu, Yingqi Qiang, Tianbo Wang, Xincheng Zhang, Yi Zhang, Liangcai Cao, Guoan Zheng

Here, we introduce a NLOS imaging technique termed ptychographic NLOS (pNLOS), which leverages coded ptychography for depth-resolved imaging of obscured objects.

Exploring the Individuality and Collectivity of Intents behind Interactions for Graph Collaborative Filtering

1 code implementation15 May 2024 Yi Zhang, Lei Sang, Yiwen Zhang

To counter the sparsity of implicit feedback, the feature distributions of users and items are encoded via a Gaussian-based graph generation strategy, and we implement the recommendation process through bilateral intent-guided graph reconstruction re-sampling.

Collaborative Filtering Graph Generation +2

IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues

no code implementations15 May 2024 Diji Yang, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang, Jie Yang, Yi Zhang

Although the Retrieval-Augmented Generation (RAG) paradigms can use external knowledge to enhance and ground the outputs of Large Language Models (LLMs) to mitigate generative hallucinations and static knowledge base problems, they still suffer from limited flexibility in adopting Information Retrieval (IR) systems with varying capabilities, constrained interpretability during the multi-round retrieval process, and a lack of end-to-end optimization.

Information Retrieval Question Answering +2

Dual-domain Collaborative Denoising for Social Recommendation

no code implementations8 May 2024 Wenjie Chen, Yi Zhang, Honghao Li, Lei Sang, Yiwen Zhang

The embedding-space collaborative denoising module devotes to resisting the noise cross-domain diffusion problem through contrastive learning with dual-domain embedding collaborative perturbation.

Contrastive Learning Denoising +1

TF4CTR: Twin Focus Framework for CTR Prediction via Adaptive Sample Differentiation

1 code implementation6 May 2024 Honghao Li, Yiwen Zhang, Yi Zhang, Lei Sang, Yun Yang

Specifically, the framework employs the SSEM at the bottom of the model to differentiate between samples, thereby assigning a more suitable encoder for each sample.

Click-Through Rate Prediction Recommendation Systems

Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes

no code implementations6 May 2024 Damin Zhang, Yi Zhang, Geetanjali Bihani, Julia Rayz

With the impressive performance in various downstream tasks, large language models (LLMs) have been widely integrated into production pipelines, like recruitment and recommendation systems.

Decision Making Fairness +2

Responsible AI: Portraits with Intelligent Bibliometrics

no code implementations5 May 2024 Yi Zhang, Mengjia Wu, Guangquan Zhang, Jie Lu

Shifting the focus from principles to practical implementation, responsible artificial intelligence (AI) has garnered considerable attention across academia, industry, and society at large.

One Subgraph for All: Efficient Reasoning on Opening Subgraphs for Inductive Knowledge Graph Completion

no code implementations24 Apr 2024 Zhiwen Xie, Yi Zhang, Guangyou Zhou, Jin Liu, Xinhui Tu, Jimmy Xiangji Huang

Knowledge Graph Completion (KGC) has garnered massive research interest recently, and most existing methods are designed following a transductive setting where all entities are observed during training.

Graph Classification Inductive knowledge graph completion

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

1 code implementation22 Apr 2024 Marah Abdin, Sam Ade Jacobs, Ammar Ahmad Awan, Jyoti Aneja, Ahmed Awadallah, Hany Awadalla, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Jianmin Bao, Harkirat Behl, Alon Benhaim, Misha Bilenko, Johan Bjorck, Sébastien Bubeck, Qin Cai, Martin Cai, Caio César Teodoro Mendes, Weizhu Chen, Vishrav Chaudhary, Dong Chen, Dongdong Chen, Yen-Chun Chen, Yi-Ling Chen, Parul Chopra, Xiyang Dai, Allie Del Giorno, Gustavo de Rosa, Matthew Dixon, Ronen Eldan, Victor Fragoso, Dan Iter, Mei Gao, Min Gao, Jianfeng Gao, Amit Garg, Abhishek Goswami, Suriya Gunasekar, Emman Haider, Junheng Hao, Russell J. Hewett, Jamie Huynh, Mojan Javaheripi, Xin Jin, Piero Kauffmann, Nikos Karampatziakis, Dongwoo Kim, Mahoud Khademi, Lev Kurilenko, James R. Lee, Yin Tat Lee, Yuanzhi Li, Yunsheng Li, Chen Liang, Lars Liden, Ce Liu, Mengchen Liu, Weishung Liu, Eric Lin, Zeqi Lin, Chong Luo, Piyush Madan, Matt Mazzola, Arindam Mitra, Hardik Modi, Anh Nguyen, Brandon Norick, Barun Patra, Daniel Perez-Becker, Thomas Portet, Reid Pryzant, Heyang Qin, Marko Radmilac, Corby Rosset, Sambudha Roy, Olatunji Ruwase, Olli Saarikivi, Amin Saied, Adil Salim, Michael Santacroce, Shital Shah, Ning Shang, Hiteshi Sharma, Swadheen Shukla, Xia Song, Masahiro Tanaka, Andrea Tupini, Xin Wang, Lijuan Wang, Chunyu Wang, Yu Wang, Rachel Ward, Guanhua Wang, Philipp Witte, Haiping Wu, Michael Wyatt, Bin Xiao, Can Xu, Jiahang Xu, Weijian Xu, Sonali Yadav, Fan Yang, Jianwei Yang, ZiYi Yang, Yifan Yang, Donghan Yu, Lu Yuan, Chengruidong Zhang, Cyril Zhang, Jianwen Zhang, Li Lyna Zhang, Yi Zhang, Yue Zhang, Yunan Zhang, Xiren Zhou

We introduce phi-3-mini, a 3. 8 billion parameter language model trained on 3. 3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3. 5 (e. g., phi-3-mini achieves 69% on MMLU and 8. 38 on MT-bench), despite being small enough to be deployed on a phone.

Language Modelling

Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval

no code implementations15 Apr 2024 Peter Baile Chen, Yi Zhang, Dan Roth

Retrieving relevant tables containing the necessary information to accurately answer a given question over tables is critical to open-domain question-answering (QA) systems.

Open-Domain Question Answering Re-Ranking +1

Enhancing Mobile "How-to" Queries with Automated Search Results Verification and Reranking

no code implementations13 Apr 2024 Lei Ding, Jeshwanth Bheemanpally, Yi Zhang

This paper introduces a novel approach to improving the accuracy and relevance of online technical support search results through automated search results verification and reranking.

AI Agent

Inference-Time Rule Eraser: Distilling and Removing Bias Rules to Mitigate Bias in Deployed Models

no code implementations7 Apr 2024 Yi Zhang, Jitao Sang

Machine learning models often make predictions based on biased features such as gender, race, and other social attributes, posing significant fairness risks, especially in societal applications, such as hiring, banking, and criminal justice.

Decision Making Fairness

A Transfer Learning Causal Approach to Evaluate Racial/Ethnic and Geographic Variation in Outcomes Following Congenital Heart Surgery

no code implementations21 Mar 2024 Larry Han, Yi Zhang, Meena Nathan, John E. Mayer, Jr., Sara K. Pasquali, Katya Zelevinsky, Rui Duan, Sharon-Lise T. Normand

Using the Society of Thoracic Surgeons' Congenital Heart Surgery Database (STS-CHSD), we focus on a national cohort of patients undergoing the Norwood operation from 2016-2022 to assess operative mortality and morbidity outcomes across U. S. geographic regions by race/ethnicity.

Causal Inference STS +2

Accurately Predicting Probabilities of Safety-Critical Rare Events for Intelligent Systems

no code implementations20 Mar 2024 Ruoxuan Bai, Jingxuan Yang, Weiduo Gong, Yi Zhang, QIUJING LU, Shuo Feng

The complexity of predicting criticality arises from the extreme data imbalance caused by rare events in high dimensional variables associated with the rare events, a challenge we refer to as the curse of rarity.

Test-time Distribution Learning Adapter for Cross-modal Visual Reasoning

no code implementations10 Mar 2024 Yi Zhang, Ce Zhang

Several approaches aim to efficiently adapt VLP models to downstream tasks with limited supervision, aiming to leverage the acquired knowledge from VLP models.

Human-Object Interaction Detection Visual Reasoning

Evacuation Management Framework towards Smart City-wide Intelligent Emergency Interactive Response System

no code implementations7 Mar 2024 Anuj Abraham, Yi Zhang, Shitala Prasad

A smart city solution toward future 6G network deployment allows small and medium sized enterprises (SMEs), industry, and government entities to connect with the infrastructures and play a crucial role in enhancing emergency preparedness with advanced sensors.

Management Sensor Fusion

Relaxometry Guided Quantitative Cardiac Magnetic Resonance Image Reconstruction

1 code implementation1 Mar 2024 Yidong Zhao, Yi Zhang, Qian Tao

Deep learning-based methods have achieved prestigious performance for magnetic resonance imaging (MRI) reconstruction, enabling fast imaging for many clinical applications.

MRI Reconstruction

Adaptive Testing Environment Generation for Connected and Automated Vehicles with Dense Reinforcement Learning

no code implementations29 Feb 2024 Jingxuan Yang, Ruoxuan Bai, Haoyuan Ji, Yi Zhang, Jianming Hu, Shuo Feng

A common approach involves designing testing scenarios based on prior knowledge of CAVs (e. g., surrogate models), conducting tests in these scenarios, and subsequently evaluating CAVs' safety performances.

regression reinforcement-learning

FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization

no code implementations28 Feb 2024 Yi Zhang, Fei Yang, Shuang Peng, Fangyu Wang, Aimin Pan

The 4-bit matrix multiplication introduced in the FlattenQuant method can effectively address the compute-bound caused by large matrix calculation.


Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology

2 code implementations CVPR 2024 Wenhao Tang, Fengtao Zhou, Sheng Huang, Xiang Zhu, Yi Zhang, Bo Liu

Unlike existing works that focus on pre-training powerful feature extractor or designing sophisticated instance aggregator, R$^2$T is tailored to re-embed instance features online.

Multiple Instance Learning

ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation

1 code implementation23 Feb 2024 Yi Zhang, Yun Tang, Wenjie Ruan, Xiaowei Huang, Siddartha Khastgir, Paul Jennings, Xingyu Zhao

Text-to-Image (T2I) Diffusion Models (DMs) have shown impressive abilities in generating high-quality images based on simple text descriptions.

TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization

1 code implementation20 Feb 2024 Liyan Tang, Igor Shalyminov, Amy Wing-mei Wong, Jon Burnsky, Jake W. Vincent, Yu'an Yang, Siffi Singh, Song Feng, Hwanjun Song, Hang Su, Lijia Sun, Yi Zhang, Saab Mansour, Kathleen McKeown

We find that there are diverse errors and error distributions in model-generated summaries and that non-LLM based metrics can capture all error types better than LLM-based evaluators.

Hallucination News Summarization +2

Leveraging Opposite Gender Interaction Ratio as a Path towards Fairness in Online Dating Recommendations Based on User Sexual Orientation

no code implementations19 Feb 2024 Yuying Zhao, Yu Wang, Yi Zhang, Pamela Wisniewski, Charu Aggarwal, Tyler Derr

While recommender systems have been designed to improve the user experience in dating platforms by providing personalized recommendations, increasing concerns about fairness have encouraged the development of fairness-aware recommender systems from various perspectives (e. g., gender and race).

Fairness Recommendation Systems +1

Few-Shot Scenario Testing for Autonomous Vehicles Based on Neighborhood Coverage and Similarity

no code implementations2 Feb 2024 Shu Li, Jingxuan Yang, Honglin He, Yi Zhang, Jianming Hu, Shuo Feng

To alleviate the considerable uncertainty inherent in a small testing scenario set, we frame the FST problem as an optimization problem and search for the testing scenario set based on neighborhood coverage and similarity.

Autonomous Vehicles

Spectrum-guided Feature Enhancement Network for Event Person Re-Identification

no code implementations2 Feb 2024 Hongchen Tan, Yi Zhang, Xiuping Liu, BaoCai Yin, Nan Ma, Xin Li, Huchuan Lu

This network consists of two innovative components: the Multi-grain Spectrum Attention Mechanism (MSAM) and the Consecutive Patch Dropout Module (CPDM).

Person Re-Identification

Choroidal thinning assessment through facial video analysis

no code implementations29 Jan 2024 Qinghua He, Yi Zhang, Mengxi Shen, Giovanni Gregori, Philip J. Rosenfeld, Ruikang K. Wang

Different features of skin are associated with various medical conditions and provide opportunities to evaluate and monitor body health.

Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Them

no code implementations22 Jan 2024 Chao Liu, Boxi Chen, Wei Shao, Chris Zhang, Kelvin Wong, Yi Zhang

Through our comprehensive review and analysis, this paper seeks to contribute to the ongoing discourse on ML-based IoT security, offering valuable insights and practical solutions to secure ML models and data in the rapidly expanding field of artificial intelligence in IoT.

Anomaly Detection Model extraction

SAM-dPCR: Real-Time and High-throughput Absolute Quantification of Biological Samples Using Zero-Shot Segment Anything Model

no code implementations22 Jan 2024 Yuanyuan Wei, Shanhang Luo, Changran Xu, Yingqi Fu, Qingyue Dong, Yi Zhang, Fuyang Qu, Guangyao Cheng, Yi-Ping Ho, Ho-Pui Ho, Wu Yuan

This accessible, cost-effective tool transcends the limitations of traditional detection methods or fully supervised AI models, marking the first application of SAM in nucleic acid detection or molecular diagnostics.

Self-Supervised Learning

Concept-Guided Prompt Learning for Generalization in Vision-Language Models

no code implementations15 Jan 2024 Yi Zhang, Ce Zhang, Ke Yu, Yushun Tang, Zhihai He

However, for generalization tasks, the current fine-tuning methods for CLIP, such as CoOp and CoCoOp, demonstrate relatively low performance on some fine-grained datasets.

Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk

no code implementations10 Jan 2024 Dennis Ulmer, Elman Mansimov, Kaixiang Lin, Justin Sun, Xibin Gao, Yi Zhang

This metric is used to filter the generated conversational data that is fed back in LLM for training.

AI and Generative AI for Research Discovery and Summarization

no code implementations8 Jan 2024 Mark Glickman, Yi Zhang

AI and generative AI tools, including chatbots like ChatGPT that rely on large language models (LLMs), have burst onto the scene this year, creating incredible opportunities to increase work productivity and improve our lives.

Aircraft Landing Time Prediction with Deep Learning on Trajectory Images

no code implementations2 Jan 2024 Liping Huang, Sheng Zhang, YiCheng Zhang, Yi Zhang, Yifang Yin

Aircraft landing time (ALT) prediction is crucial for air traffic management, especially for arrival aircraft sequencing on the runway.

EasyDrag: Efficient Point-based Manipulation on Diffusion Models

1 code implementation CVPR 2024 Xingzhong Hou, Boxiao Liu, Yi Zhang, Jihao Liu, Yu Liu, Haihang You

Generative models are gaining increasing popularity and the demand for precisely generating images is on the rise.

Image Manipulation

Domain Separation Graph Neural Networks for Saliency Object Ranking

no code implementations CVPR 2024 Zijian Wu, Jun Lu, Jing Han, Lianfa Bai, Yi Zhang, Zhuang Zhao, Siyang Song

Then we propose a Shape-Texture Graph Domain Separation (STGDS) module to separate the task-relevant and irrelevant information of target objects by explicitly modelling the relationship between each pair of objects in terms of their shapes and textures respectively.

Graph Neural Network

CETN: Contrast-enhanced Through Network for CTR Prediction

1 code implementation15 Dec 2023 Honghao Li, Lei Sang, Yi Zhang, Xuyun Zhang, Yiwen Zhang

Click-through rate (CTR) Prediction is a crucial task in personalized information retrievals, such as industrial recommender systems, online advertising, and web search.

Click-Through Rate Prediction Contrastive Learning +1

TinyGSM: achieving >80% on GSM8k with small language models

no code implementations14 Dec 2023 Bingbin Liu, Sebastien Bubeck, Ronen Eldan, Janardhan Kulkarni, Yuanzhi Li, Anh Nguyen, Rachel Ward, Yi Zhang

Specifically for solving grade school math, the smallest model size so far required to break the 80\% barrier on the GSM8K benchmark remains to be 34B.

Arithmetic Reasoning GSM8K +2

PairingNet: A Learning-based Pair-searching and -matching Network for Image Fragments

no code implementations14 Dec 2023 Rixin Zhou, Ding Xia, Yi Zhang, Honglin Pang, Xi Yang, Chuntao Li

In this paper, we propose a learning-based image fragment pair-searching and -matching approach to solve the challenging restoration problem.

Prompted Contextual Transformer for Incomplete-View CT Reconstruction

1 code implementation13 Dec 2023 Chenglong Ma, Zilong Li, Junjun He, Junping Zhang, Yi Zhang, Hongming Shan

To enjoy the multi-setting synergy in a single model, we propose a novel Prompted Contextual Transformer (ProCT) for incomplete-view CT reconstruction.

Computed Tomography (CT)

FedReverse: Multiparty Reversible Deep Neural Network Watermarking

no code implementations10 Dec 2023 Junlong Mao, Huiyi Tang, Yi Zhang, Fengxia Liu, Zhiyong Zheng, Shanxiang Lyu

The simulations demonstrate FedReverse's robustness, reversibility, and minimal impact on model accuracy across varying embedding parameters and multiple client scenarios.

Positional Description Matters for Transformers Arithmetic

no code implementations22 Nov 2023 Ruoqi Shen, Sébastien Bubeck, Ronen Eldan, Yin Tat Lee, Yuanzhi Li, Yi Zhang

For (i) we train a small model on a small dataset (100M parameters and 300k samples) with remarkable aptitude in (direct, no scratchpad) 15 digits multiplication and essentially perfect up to 12 digits, while usual training in this context would give a model failing at 4 digits multiplication.


Point, Segment and Count: A Generalized Framework for Object Counting

1 code implementation21 Nov 2023 Zhizhong Huang, Mingliang Dai, Yi Zhang, Junping Zhang, Hongming Shan

In this paper, we propose a generalized framework for both few-shot and zero-shot object counting based on detection.

Knowledge Distillation Object +3

Energizing Federated Learning via Filter-Aware Attention

no code implementations18 Nov 2023 Ziyuan Yang, Zerui Shao, Huijie Huangfu, Hui Yu, Andrew Beng Jin Teoh, Xiaoxiao Li, Hongming Shan, Yi Zhang

Federated learning (FL) is a promising distributed paradigm, eliminating the need for data sharing but facing challenges from data heterogeneity.

Federated Learning

PT-Tuning: Bridging the Gap between Time Series Masked Reconstruction and Forecasting via Prompt Token Tuning

no code implementations7 Nov 2023 Hao liu, Jinrui Gan, Xiaoxuan Fan, Yi Zhang, Chuanxian Luo, Jing Zhang, Guangxin Jiang, Yucheng Qian, Changwei Zhao, Huan Ma, Zhenyu Guo

In this paper, we first point out that the unification of task objectives and adaptation for task difficulty are critical for bridging the gap between time series masked reconstruction and forecasting.

Decoder Representation Learning +2

Deep Image Semantic Communication Model for Artificial Intelligent Internet of Things

2 code implementations6 Nov 2023 Li Ping Qian, Yi Zhang, Sikai Lyu, Huijie Zhu, Yuan Wu, Xuemin Sherman Shen, Xiaoniu Yang

Particularly, at the transmitter side, a high-precision image semantic segmentation algorithm is proposed to extract the semantic information of the image to achieve significant compression of the image data.

Generative Adversarial Network Image Compression +3

Individualized Policy Evaluation and Learning under Clustered Network Interference

no code implementations4 Nov 2023 Yi Zhang, Kosuke Imai

Under this model, we propose an estimator that can be used to evaluate the empirical performance of an ITR.

Contrast-Agnostic Groupwise Registration by Robust PCA for Quantitative Cardiac MRI

no code implementations3 Nov 2023 Xinqi Li, Yi Zhang, Yidong Zhao, Jan van Gemert, Qian Tao

To address the challenge, we propose a novel motion correction framework based on robust principle component analysis (rPCA) that decomposes quantitative cardiac MRI into low-rank and sparse components, and we integrate the groupwise CNN-based registration backbone within the rPCA framework.

Learning to Adapt CLIP for Few-Shot Monocular Depth Estimation

no code implementations2 Nov 2023 Xueting Hu, Ce Zhang, Yi Zhang, Bowen Hai, Ke Yu, Zhihai He

When CLIP is used for depth estimation tasks, the patches, divided from the input images, can be combined with a series of semantic descriptions of the depth information to obtain similarity results.

Monocular Depth Estimation

Privacy-Preserving Encrypted Low-Dose CT Denoising

no code implementations13 Oct 2023 Ziyuan Yang, Huijie Huangfu, Maosong Ran, Zhiwen Wang, Hui Yu, Yi Zhang

In this way, the proposed methods can achieve two merits, the data privacy is well protected and the server model is free from the risk of model leakage.

Denoising Privacy Preserving

Resilient Model-Free Asymmetric Bipartite Consensus for Nonlinear Multi-Agent Systems against DoS Attacks

no code implementations29 Sep 2023 Yi Zhang, Yichao Wang, Junbo Zhao, Shan Zuo

In this letter, we study an unified resilient asymmetric bipartite consensus (URABC) problem for nonlinear multi-agent systems with both cooperative and antagonistic interactions under denial-of-service (DoS) attacks.

Stackelberg Driver Model for Continual Policy Improvement in Scenario-Based Closed-Loop Autonomous Driving

1 code implementation25 Sep 2023 Haoyi Niu, Qimao Chen, Yingyue Li, Yi Zhang, Jianming Hu

The deployment of autonomous vehicles (AVs) has faced hurdles due to the dominance of rare but critical corner cases within the long-tail distribution of driving scenarios, which negatively affects their overall performance.

Autonomous Driving

User Simulation with Large Language Models for Evaluating Task-Oriented Dialogue

no code implementations23 Sep 2023 Sam Davidson, Salvatore Romeo, Raphael Shu, James Gung, Arshit Gupta, Saab Mansour, Yi Zhang

One of the major impediments to the development of new task-oriented dialogue (TOD) systems is the need for human evaluation at multiple stages and iterations of the development process.

In-Context Learning User Simulation

DeepAdaIn-Net: Deep Adaptive Device-Edge Collaborative Inference for Augmented Reality

no code implementations IEEE Journal of Selected Topics in Signal Processing 2023 Li Wang, Xin Wu, Yi Zhang, Xinyun Zhang, LianmingXu, Zhihua Wu, Aiguo Fei

Specifically, DeepAdaIn-Net encompasses a partition point selection (PPS) module, a high feature compression learning (HFCL) module, a bandwidth-aware feature configuration (BaFC) module, and a feature consistency compensation (FCC) module.

Collaborative Inference Feature Compression +2

Supervised Stochastic Neighbor Embedding Using Contrastive Learning

1 code implementation15 Sep 2023 Yi Zhang

Stochastic neighbor embedding (SNE) methods $t$-SNE, UMAP are two most popular dimensionality reduction methods for data visualization.

Contrastive Learning Data Visualization +1

Balanced and Explainable Social Media Analysis for Public Health with Large Language Models

1 code implementation12 Sep 2023 Yan Jiang, Ruihong Qiu, Yi Zhang, Peng-Fei Zhang

Furthermore, an LLMs explanation mechanism is proposed by prompting an LLM with the predicted results from BERT models.

Data Augmentation Decision Making

UQ at #SMM4H 2023: ALEX for Public Health Analysis with Social Media

1 code implementation8 Sep 2023 Yan Jiang, Ruihong Qiu, Yi Zhang, Zi Huang

As social media becomes increasingly popular, more and more activities related to public health emerge.

Data Augmentation Task 2

BDC-Adapter: Brownian Distance Covariance for Better Vision-Language Reasoning

no code implementations3 Sep 2023 Yi Zhang, Ce Zhang, Zihan Liao, Yushun Tang, Zhihai He

Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP and ALIGN, have introduced a new paradigm for learning transferable visual representations.

A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications

1 code implementation31 Aug 2023 Yi Zhang, Yuying Zhao, Zhaoqing Li, Xueqi Cheng, Yu Wang, Olivera Kotevska, Philip S. Yu, Tyler Derr

Despite this progress, there is a lack of a comprehensive overview of the attacks and the techniques for preserving privacy in the graph domain.

Privacy Preserving

Unsupervised Prototype Adapter for Vision-Language Models

no code implementations22 Aug 2023 Yi Zhang, Ce Zhang, Xueting Hu, Zhihai He

To leverage the valuable knowledge encoded within these models for downstream tasks, several fine-tuning approaches, including prompt tuning methods and adapter-based methods, have been developed to adapt vision-language models effectively with supervision.

Domain Generalization

FocalDreamer: Text-driven 3D Editing via Focal-fusion Assembly

no code implementations21 Aug 2023 Yuhan Li, Yishun Dou, Yue Shi, Yu Lei, Xuanhong Chen, Yi Zhang, Peng Zhou, Bingbing Ni

While text-3D editing has made significant strides in leveraging score distillation sampling, emerging approaches still fall short in delivering separable, precise and consistent outcomes that are vital to content creation.

Tackling Vision Language Tasks Through Learning Inner Monologues

no code implementations19 Aug 2023 Diji Yang, Kezhen Chen, Jinmeng Rao, Xiaoyuan Guo, Yawen Zhang, Jie Yang, Yi Zhang

Visual language tasks require AI models to comprehend and reason with both visual and textual content.

3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation

1 code implementation ICCV 2023 Yi Zhang, Pengliang Ji, Angtian Wang, Jieru Mei, Adam Kortylewski, Alan Yuille

Motivated by the recent success of generative models in rigid object pose estimation, we propose 3D-aware Neural Body Fitting (3DNBF) - an approximate analysis-by-synthesis approach to 3D human pose estimation with SOTA performance and occlusion robustness.

3D Human Pose Estimation Contrastive Learning

Comprehensive Competition Mechanism in Palmprint Recognition

1 code implementation IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2023 Ziyuan Yang, Huijie Huangfu, Lu Leng, Bob Zhang, Andrew Beng Jin Teoh, Yi Zhang

The traditional competition mechanism focuses solely on selecting the winner of different channels without considering the spatial information of the features.

Benign Shortcut for Debiasing: Fair Visual Recognition via Intervention with Shortcut Features

no code implementations13 Aug 2023 Yi Zhang, Jitao Sang, Junyang Wang, Dongmei Jiang, YaoWei Wang

To this end, we propose \emph{Shortcut Debiasing}, to first transfer the target task's learning of bias attributes from bias features to shortcut features, and then employ causal intervention to eliminate shortcut features during inference.


FoodSAM: Any Food Segmentation

1 code implementation11 Aug 2023 Xing Lan, Jiayi Lyu, Hanyu Jiang, Kun Dong, Zehai Niu, Yi Zhang, Jian Xue

Remarkably, this pioneering framework stands as the first-ever work to achieve instance, panoptic, and promptable segmentation on food images.

 Ranked #1 on Semantic Segmentation on FoodSeg103 (using extra training data)

Image Segmentation Instance Segmentation +2

Facial Prior Based First Order Motion Model for Micro-expression Generation

1 code implementation8 Aug 2023 Yi Zhang, Youjun Zhao, Yuhang Wen, Zixuan Tang, Xinhua Xu, Mengyuan Liu

To solve this problem, this paper tries to formulate a new task called micro-expression generation and then presents a strong baseline which combines the first order motion model with facial prior knowledge.

Micro-expression Generation (MEGC2021) motion prediction

Unsupervised Camouflaged Object Segmentation as Domain Adaptation

1 code implementation8 Aug 2023 Yi Zhang, Chengyi Wu

To this end, we formulate the UCOS as a source-free unsupervised domain adaptation task (UCOS-DA), where both source labels and target labels are absent during the whole model training process.

Attribute Camouflaged Object Segmentation +6

Physics-Driven Spectrum-Consistent Federated Learning for Palmprint Verification

1 code implementation1 Aug 2023 Ziyuan Yang, Andrew Beng Jin Teoh, Bob Zhang, Lu Leng, Yi Zhang

Subsequently, we introduce anchor models for short- and long-spectrum, which constrain the optimization directions of local models associated with long- and short-spectrum images.

Federated Learning

Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification

1 code implementation ICCV 2023 Wenhao Tang, Sheng Huang, Xiaoxian Zhang, Fengtao Zhou, Yi Zhang, Bo Liu

Moreover, the student is used to update the teacher with an exponential moving average (EMA), which in turn identifies new hard instances for subsequent training iterations and stabilizes the optimization.

Image Classification Multiple Instance Learning

Cross-Modal Concept Learning and Inference for Vision-Language Models

no code implementations28 Jul 2023 Yi Zhang, Ce Zhang, Yushun Tang, Zhihai He

Based on these visual concepts, we construct a discriminative representation of images and learn a concept inference network to perform downstream image classification tasks, such as few-shot learning and domain generalization.

Domain Generalization Few-Shot Learning +1

ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising

1 code implementation23 Jul 2023 Zhihao Chen, Qi Gao, Yi Zhang, Hongming Shan

In this paper, we propose a novel Anatomy-aware Supervised CONtrastive learning framework, termed ASCON, which can explore the anatomical semantics for low-dose CT denoising while providing anatomical interpretability.

Anatomy Computed Tomography (CT) +2

FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstruction

1 code implementation12 Jul 2023 Chenglong Ma, Zilong Li, Junping Zhang, Yi Zhang, Hongming Shan

Specifically, we first propose a frequency-band-aware artifact modeling network (FreeNet), which learns artifact-related frequency-band attention in Fourier domain for better modeling the globally distributed streak artifact on the sparse-view CT images.

Computed Tomography (CT)

Leveraging GPT-4 for Food Effect Summarization to Enhance Product-Specific Guidance Development via Iterative Prompting

no code implementations28 Jun 2023 Yiwen Shi, Ping Ren, Jing Wang, Biao Han, Taha ValizadehAslani, Felix Agbavor, Yi Zhang, Meng Hu, Liang Zhao, Hualou Liang

Specifically, we propose a three-turn iterative prompting approach to food effect summarization in which the keyword-focused and length-controlled prompts are respectively provided in consecutive turns to refine the quality of the generated summary.

Text Summarization

A Unified Framework for Solving a General Class of Nonconvexly Regularized Convex Models

no code implementations26 Jun 2023 Yi Zhang, Isao Yamada

Recently, several nonconvex sparse regularizers which can preserve the convexity of the cost function have received increasing attention.

Generating Images with 3D Annotations Using Diffusion Models

no code implementations13 Jun 2023 Wufei Ma, Qihao Liu, Jiahao Wang, Angtian Wang, Xiaoding Yuan, Yi Zhang, Zihao Xiao, Guofeng Zhang, Beijia Lu, Ruxiao Duan, Yongrui Qi, Adam Kortylewski, Yaoyao Liu, Alan Yuille

With explicit 3D geometry control, we can easily change the 3D structures of the objects in the generated images and obtain ground-truth 3D annotations automatically.

3D Pose Estimation Style Transfer

ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems

no code implementations7 Jun 2023 Yi Zhang, Jan Deriu, George Katsogiannis-Meimarakis, Catherine Kosten, Georgia Koutrika, Kurt Stockinger

Thus, the challenge is many-fold: creating NL-to-SQL systems for highly complex domains with a small amount of hand-made training data augmented with synthetic data.

Controllable Text-to-Image Generation with GPT-4

no code implementations29 May 2023 Tianjun Zhang, Yi Zhang, Vibhav Vineet, Neel Joshi, Xin Wang

Control-GPT works by querying GPT-4 to write TikZ code, and the generated sketches are used as references alongside the text instructions for diffusion models (e. g., ControlNet) to generate photo-realistic images.

Instruction Following Text-to-Image Generation

Measuring and Mitigating Constraint Violations of In-Context Learning for Utterance-to-API Semantic Parsing

no code implementations24 May 2023 Shufan Wang, Sebastien Jean, Sailik Sengupta, James Gung, Nikolaos Pappas, Yi Zhang

In executable task-oriented semantic parsing, the system aims to translate users' utterances in natural language to machine-interpretable programs (API calls) that can be executed according to pre-defined API specifications.

In-Context Learning Retrieval +2

NatCS: Eliciting Natural Customer Support Dialogues

2 code implementations4 May 2023 James Gung, Emily Moeng, Wesley Rose, Arshit Gupta, Yi Zhang, Saab Mansour

Existing task-oriented dialogue datasets, which were collected to benchmark dialogue systems mainly in written human-to-bot settings, are not representative of real customer support conversations and do not provide realistic benchmarks for systems that are applied to natural data.

Dialogue Act Classification

From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping

1 code implementation26 Apr 2023 Junyang Wang, Ming Yan, Yi Zhang, Jitao Sang

Although previous works have created generation capacity for CLIP through additional language models, a modality gap between the CLIP representations of different modalities and the inability of CLIP to model the offset of this gap, which fails the concept to transfer across modalities.

Decoder Image Captioning +4

Intent Induction from Conversations for Task-Oriented Dialogue Track at DSTC 11

2 code implementations25 Apr 2023 James Gung, Raphael Shu, Emily Moeng, Wesley Rose, Salvatore Romeo, Yassine Benajiba, Arshit Gupta, Saab Mansour, Yi Zhang

With increasing demand for and adoption of virtual assistants, recent work has investigated ways to accelerate bot schema design through the automatic induction of intents or the induction of slots and dialogue states.

Synthetic Datasets for Autonomous Driving: A Survey

no code implementations24 Apr 2023 Zhihang Song, Zimin He, Xingyu Li, Qiming Ma, Ruibo Ming, Zhiqi Mao, Huaxin Pei, Lihui Peng, Jianming Hu, Danya Yao, Yi Zhang

In this paper, we summarize the evolution of synthetic dataset generation methods and review the work to date in synthetic datasets related to single and multi-task categories for to autonomous driving study.

Autonomous Driving

NeRF applied to satellite imagery for surface reconstruction

1 code implementation9 Apr 2023 Federico Semeraro, Yi Zhang, Wenying Wu, Patrick Carroll

S-NeRF improves on the standard Neural Radiance Field (NeRF) method by considering the radiance as a function of the albedo and the irradiance.

Surface Reconstruction

CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization

1 code implementation4 Apr 2023 Qi Gao, Zilong Li, Junping Zhang, Yi Zhang, Hongming Shan

First, CoreDiff utilizes LDCT images to displace the random Gaussian noise and employs a novel mean-preserving degradation operator to mimic the physical process of CT degradation, significantly reducing sampling steps thanks to the informative LDCT images as the starting point of the sampling process.

Computed Tomography (CT) Denoising +1

Sparks of Artificial General Intelligence: Early experiments with GPT-4

2 code implementations22 Mar 2023 Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, Harsha Nori, Hamid Palangi, Marco Tulio Ribeiro, Yi Zhang

We contend that (this early version of) GPT-4 is part of a new cohort of LLMs (along with ChatGPT and Google's PaLM for example) that exhibit more general intelligence than previous AI models.

Arithmetic Reasoning Math Word Problem Solving

Frequency-Modulated Point Cloud Rendering with Easy Editing

1 code implementation CVPR 2023 Yi Zhang, Xiaoyang Huang, Bingbing Ni, Teng Li, Wenjun Zhang

We develop an effective point cloud rendering pipeline for novel view synthesis, which enables high fidelity local detail reconstruction, real-time rendering and user-friendly editing.

Novel View Synthesis SSIM

KBNet: Kernel Basis Network for Image Restoration

1 code implementation6 Mar 2023 Yi Zhang, Dasong Li, Xiaoyu Shi, Dailan He, Kangning Song, Xiaogang Wang, Hongwei Qin, Hongsheng Li

In this paper, we propose a kernel basis attention (KBA) module, which introduces learnable kernel bases to model representative image patterns for spatial information aggregation.

Color Image Denoising Deblurring +4

Augmented smartphone bilirubinometer enabled by a mobile app that turns smartphone into multispectral imager

no code implementations4 Mar 2023 Qinghua He, Wanyu Li, Yaping Shi, Yi Yu, Yi Zhang, Wenqian Geng, Zhiyuan Sun, Ruikang K Wang

This study highlights the potential of SpeCamX to improve the prediction of bio-chromophores, and its ability to transform an ordinary smartphone into a powerful medical tool without the need for additional investments or expertise.

Conversation Style Transfer using Few-Shot Learning

no code implementations16 Feb 2023 Shamik Roy, Raphael Shu, Nikolaos Pappas, Elman Mansimov, Yi Zhang, Saab Mansour, Dan Roth

Conventional text style transfer approaches focus on sentence-level style transfer without considering contextual information, and the style is described with attributes (e. g., formality).

Few-Shot Learning In-Context Learning +5

POSGen: Personalized Opening Sentence Generation for Online Insurance Sales

no code implementations10 Feb 2023 Yu Li, Yi Zhang, Weijia Wu, Zimu Zhou, Qiang Li

Such personalized opening sentence generation is challenging because (i) there are limited historical samples for conversation topic recommendation in online insurance sales and (ii) existing text generation schemes often fail to support customized topic ordering based on user preferences.

Chatbot Management +2

Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion

no code implementations4 Feb 2023 Yi-An Lai, Elman Mansimov, Yuqing Xie, Yi Zhang

When upgrading neural models to a newer version, new errors that were not encountered in the legacy version can be introduced, known as regression errors.


Hierarchical Disentangled Representation for Invertible Image Denoising and Beyond

no code implementations31 Jan 2023 Wenchao Du, Hu Chen, Yi Zhang, H. Yang

More specifically, we decompose the noisy image into clean low-frequency and hybrid high-frequency parts with an invertible transformation and then disentangle case-specific noise and high-frequency components in the latent space.

Image Denoising Image Restoration

Optimization and scheduling for a large scale urban transportation system in a fast-changing world

no code implementations28 Jan 2023 Yi Zhang

This paper proposes a set of technological solutions to transform existing transport systems into more intelligent, interactive systems by utilizing optimization and control methods that can be implemented in the near future.

Model Predictive Control Scheduling

Backward Compatibility During Data Updates by Weight Interpolation

no code implementations25 Jan 2023 Raphael Schumann, Elman Mansimov, Yi-An Lai, Nikolaos Pappas, Xibin Gao, Yi Zhang

This method interpolates between the weights of the old and new model and we show in extensive experiments that it reduces negative flips without sacrificing the improved accuracy of the new model.


Resilient Containment Control of Heterogeneous Multi-Agent Systems Against Unbounded Sensor and Actuator Attacks

no code implementations18 Jan 2023 Shan Zuo, Yi Zhang, Yichao Wang

To this end, we consider the resilient containment control problem of general linear heterogeneous MAS in the face of correlated and unbounded sensor attacks, as well as general unbounded actuator attacks.

Learning Shape Primitives via Implicit Convexity Regularization

1 code implementation ICCV 2023 Xiaoyang Huang, Yi Zhang, Kai Chen, Teng Li, Wenjun Zhang, Bingbing Ni

In this work, a novel regularization term named Implicit Convexity Regularization (ICR) imposed on implicit primitive learning is proposed to tackle this problem.

Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue Systems

1 code implementation15 Dec 2022 Denis Emelin, Daniele Bonadiman, Sawsan Alqahtani, Yi Zhang, Saab Mansour

Pre-trained language models (PLM) have advanced the state-of-the-art across NLP applications, but lack domain-specific knowledge that does not naturally occur in pre-training data.

Knowledge Probing Response Generation +1

Learning threshold neurons via the "edge of stability"

no code implementations14 Dec 2022 Kwangjun Ahn, Sébastien Bubeck, Sinho Chewi, Yin Tat Lee, Felipe Suarez, Yi Zhang

For these models, we provably establish the edge of stability phenomenon and discover a sharp phase transition for the step size below which the neural network fails to learn "threshold-like" neurons (i. e., neurons with a non-zero first-layer bias).

Inductive Bias

Robust Split Federated Learning for U-shaped Medical Image Networks

1 code implementation13 Dec 2022 Ziyuan Yang, Yingyu Chen, Huijie Huangfu, Maosong Ran, Hui Wang, Xiaoxiao Li, Yi Zhang

To achieve this goal, in this paper, we propose Robust Split Federated Learning (RoS-FL) for U-shaped medical image networks, which is a novel hybrid learning paradigm of FL and SL.

Federated Learning

AutoPINN: When AutoML Meets Physics-Informed Neural Networks

no code implementations8 Dec 2022 Xinle Wu, Dalin Zhang, Miao Zhang, Chenjuan Guo, Shuai Zhao, Yi Zhang, Huai Wang, Bin Yang

We then propose a resource-aware search strategy to explore the search space to find the best PINN model under different resource constraints.


HierarchyFL: Heterogeneous Federated Learning via Hierarchical Self-Distillation

no code implementations5 Dec 2022 Jun Xia, Yi Zhang, Zhihao Yue, Ming Hu, Xian Wei, Mingsong Chen

Federated learning (FL) has been recognized as a privacy-preserving distributed machine learning paradigm that enables knowledge sharing among various heterogeneous artificial intelligence (AIoT) devices through centralized global model aggregation.

Federated Learning Privacy Preserving

DFEE: Interactive DataFlow Execution and Evaluation Kit

1 code implementation4 Dec 2022 Han He, Song Feng, Daniele Bonadiman, Yi Zhang, Saab Mansour

DataFlow has been emerging as a new paradigm for building task-oriented chatbots due to its expressive semantic representations of the dialogue tasks.

Benchmarking Scheduling

Prototype matching: children's preference for forming scientific concepts

no code implementations3 Dec 2022 Zhong Wang, Yi Zhang, Yi Jiang

Children have an obvious preference for "prototype matching" in scientific concept learning, which is not only obviously deviated from the current general understanding of science education that emphasizes discovery/inquiry construction, but also points out that there may be a priority relationship among various ways of concept organization (such as definition theory, prototype theory, schema theory, etc.).

Adaptive Safety Evaluation for Connected and Automated Vehicles with Sparse Control Variates

no code implementations1 Dec 2022 Jingxuan Yang, Haowei Sun, Honglin He, Yi Zhang, Shuo Feng, Henry X. Liu

One prevailing way is to design testing scenarios using prior knowledge of CAVs, test CAVs in these scenarios, and then evaluate their safety performances.

Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment

no code implementations14 Nov 2022 Junyang Wang, Yi Zhang, Ming Yan, Ji Zhang, Jitao Sang

We further propose Anchor Augment to guide the generative model's attention to the fine-grained information in the representation of CLIP.

Computational Efficiency Image Captioning +2

Efficient and quantum-adaptive machine learning with fermion neural networks

1 code implementation10 Nov 2022 Pei-Lin Zheng, Jia-Bao Wang, Yi Zhang

Classical artificial neural networks have witnessed widespread successes in machine-learning applications.

Interpretable Machine Learning

Fair Visual Recognition via Intervention with Proxy Features

no code implementations2 Nov 2022 Yi Zhang, Jitao Sang, Junyang Wang

To this end, we propose \emph{Proxy Debiasing}, to first transfer the target task's learning of bias information from bias features to artificial proxy features, and then employ causal intervention to eliminate proxy features in inference.


Boosting Point Clouds Rendering via Radiance Mapping

1 code implementation27 Oct 2022 Xiaoyang Huang, Yi Zhang, Bingbing Ni, Teng Li, Kai Chen, Wenjun Zhang

In this work, we focus on boosting the image quality of point clouds rendering with a compact model design.

FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization

no code implementations26 Oct 2022 Junyang Wang, Yi Zhang, Jitao Sang

Although FairCLIP is used to eliminate bias in image retrieval, it achieves the neutralization of the representation which is common to all CLIP downstream tasks.

Attribute Fairness +2

NAS-PRNet: Neural Architecture Search generated Phase Retrieval Net for Off-axis Quantitative Phase Imaging

no code implementations25 Oct 2022 Xin Shu, Mengxuan Niu, Yi Zhang, Renjie Zhou

Single neural networks have achieved simultaneous phase retrieval with aberration compensation and phase unwrapping in off-axis Quantitative Phase Imaging (QPI).

Decoder Neural Architecture Search +1

What Makes Convolutional Models Great on Long Sequence Modeling?

1 code implementation17 Oct 2022 Yuhong Li, Tianle Cai, Yi Zhang, Deming Chen, Debadeepta Dey

We focus on the structure of the convolution kernel and identify two critical but intuitive principles enjoyed by S4 that are sufficient to make up an effective global convolutional model: 1) The parameterization of the convolutional kernel needs to be efficient in the sense that the number of parameters should scale sub-linearly with sequence length.

Long-range modeling

HiGNN: Hierarchical Informative Graph Neural Networks for Molecular Property Prediction Equipped with Feature-Wise Attention

1 code implementation30 Aug 2022 Weimin Zhu, Yi Zhang, Duancheng Zhao, Jianrong Xu, Ling Wang

Elucidating and accurately predicting the druggability and bioactivities of molecules plays a pivotal role in drug design and discovery and remains an open challenge.

Drug Discovery Molecular Property Prediction +2

Research on Multi-Objective Planning of Electric Vehicle Charging Stations Considering the Condition of Urban Traffic Network

no code implementations27 Aug 2022 Limeng Wang, Chao Yang, Yi Zhang, Fanjin Bu

How to weigh various factors to construct a reasonable model of charging station location and capacity has become a major difficulty in the field of electric vehicle charging facility planning.

Impact of Loss Model Selection on Power Semiconductor Lifetime Prediction in Electric Vehicles

no code implementations27 Aug 2022 Hongjian Xia, Yi Zhang, Dao Zhou, Minyou Chen, Wei Lai, Yunhai Wei, Huai Wang

Power loss estimation is an indispensable procedure to conduct lifetime prediction for power semiconductor device.

Model Selection

A non-invasive fault location method for modular multilevel converters under light load conditions

no code implementations16 Aug 2022 Yaqian Zhang, Yi Zhang, Frede Blaabjerg, Jianzhong Zhang

The proposed approach of injecting the second-order circulating current will rebuild the bipolar arm current of the MMC and enlarge the capacitor voltage deviations between the healthy and faulty SMs.

Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation

no code implementations29 Jul 2022 Qihao Liu, Yi Zhang, Song Bai, Alan Yuille

Inspired by the remarkable ability of humans to infer occluded joints from visible cues, we develop a method to explicitly model this process that significantly improves bottom-up multi-person human pose estimation with or without occlusions.

3D Human Pose Estimation 3D Multi-Person Pose Estimation (absolute) +2

Fine-Tuning BERT for Automatic ADME Semantic Labeling in FDA Drug Labeling to Enhance Product-Specific Guidance Assessment

no code implementations25 Jul 2022 Yiwen Shi, Jing Wang, Ping Ren, Taha ValizadehAslani, Yi Zhang, Meng Hu, Hualou Liang

Product-specific guidances (PSGs) recommended by the United States Food and Drug Administration (FDA) are instrumental to promote and guide generic drug product development.

Transfer Learning

Two-Stage Fine-Tuning: A Novel Strategy for Learning Class-Imbalanced Data

1 code implementation22 Jul 2022 Taha ValizadehAslani, Yiwen Shi, Jing Wang, Ping Ren, Yi Zhang, Meng Hu, Liang Zhao, Hualou Liang

Owing to this paucity of samples, learning on the tail classes is especially challenging for the fine-tuning when transferring a pretrained model to a downstream task.

text-classification Text Classification

Adaptive Testing for Connected and Automated Vehicles with Sparse Control Variates in Overtaking Scenarios

no code implementations19 Jul 2022 Jingxuan Yang, Honglin He, Yi Zhang, Shuo Feng, Henry X. Liu

To validate the proposed method, the high-dimensional overtaking scenarios are investigated, and the results demonstrate that our approach can further accelerate the evaluation process by about 30 times.


Counterfactually Measuring and Eliminating Social Bias in Vision-Language Pre-training Models

1 code implementation3 Jul 2022 Yi Zhang, Junyang Wang, Jitao Sang

Vision-Language Pre-training (VLP) models have achieved state-of-the-art performance in numerous cross-modal tasks.


Collaboration-Aware Graph Convolutional Network for Recommender Systems

1 code implementation3 Jul 2022 Yu Wang, Yuying Zhao, Yi Zhang, Tyler Derr

Graph Neural Networks (GNNs) have been successfully adopted in recommender systems by virtue of the message-passing that implicitly captures collaborative effect.

Recommendation Systems

Explanation-based Counterfactual Retraining(XCR): A Calibration Method for Black-box Models

no code implementations22 Jun 2022 Liu Zhendong, Wenyu Jiang, Yi Zhang, Chongjun Wang

With the rapid development of eXplainable Artificial Intelligence (XAI), a long line of past work has shown concerns about the Out-of-Distribution (OOD) problem in perturbation-based post-hoc XAI models and explanations are socially misaligned.

counterfactual Explainable artificial intelligence +2