Search Results for author: Zilong Wang

Found 53 papers, 20 papers with code

WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstruction

no code implementations3 Feb 2025 Zilong Wang, Zhiyang Dou, YuAn Liu, Cheng Lin, Xiao Dong, Yunhui Guo, Chenxu Zhang, Xin Li, Wenping Wang, Xiaohu Guo

In this paper, we present WonderHuman to reconstruct dynamic human avatars from a monocular video for high-fidelity novel view synthesis.

3D Human Reconstruction Novel View Synthesis

RMAvatar: Photorealistic Human Avatar Reconstruction from Monocular Video Based on Rectified Mesh-embedded Gaussians

no code implementations13 Jan 2025 Sen Peng, Weixing Xie, Zilong Wang, Xiaohu Guo, Zhonggui Chen, Baorong Yang, Xiao Dong

We introduce RMAvatar, a novel human avatar representation with Gaussian splatting embedded on mesh to learn clothed avatar from a monocular video.

mFabric: An Efficient and Scalable Fabric for Mixture-of-Experts Training

no code implementations7 Jan 2025 Xudong Liao, Yijun Sun, Han Tian, Xinchen Wan, Yilun Jin, Zilong Wang, Zhenghang Ren, Xinyang Huang, Wenxue Li, Kin Fai Tse, Zhizhen Zhong, Guyue Liu, Ying Zhang, Xiaofeng Ye, Yiming Zhang, Kai Chen

Mixture-of-Expert (MoE) models outperform conventional models by selectively activating different subnets, named \emph{experts}, on a per-token basis.

Blocking

The Potential and Value of AI Chatbot in Personalized Cognitive Training

no code implementations25 Oct 2024 Zilong Wang, Nan Chen, Luna K. Qiu, Ling Yue, Geli Guo, Yang Ou, Shiqi Jiang, Yuqing Yang, Lili Qiu

In recent years, the rapid aging of the global population has led to an increase in cognitive disorders, such as Alzheimer's disease, presenting significant public health challenges.

Chatbot

MixEHR-Nest: Identifying Subphenotypes within Electronic Health Records through Hierarchical Guided-Topic Modeling

1 code implementation17 Oct 2024 Ruohan Wang, Zilong Wang, Ziyang Song, David Buckeridge, Yue Li

Specifically, MixEHR-Nest detects multiple subtopics from each phenotype topic, whose prior is guided by the expert-curated phenotype concepts such as Phenotype Codes (PheCodes) or Clinical Classification Software (CCS) codes.

Machine Unlearning in Forgettability Sequence

no code implementations9 Oct 2024 Junjie Chen, Qian Chen, Jian Lou, XiaoYu Zhang, Kai Wu, Zilong Wang

Machine unlearning (MU) is becoming a promising paradigm to achieve the "right to be forgotten", where the training trace of any chosen data points could be eliminated, while maintaining the model utility on general testing samples after unlearning.

Machine Unlearning

TableRAG: Million-Token Table Understanding with Language Models

1 code implementation7 Oct 2024 Si-An Chen, Lesly Miculicich, Julian Martin Eisenschlos, Zifeng Wang, Zilong Wang, Yanfei Chen, Yasuhisa Fujii, Hsuan-Tien Lin, Chen-Yu Lee, Tomas Pfister

Recent advancements in language models (LMs) have notably enhanced their ability to reason with tabular data, primarily through program-aided mechanisms that manipulate and analyze tables.

RAG Retrieval

Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely

no code implementations23 Sep 2024 Siyun Zhao, Yuqing Yang, Zilong Wang, Zhiyuan He, Luna K. Qiu, Lili Qiu

In this survey, we propose a RAG task categorization method, classifying user queries into four levels based on the type of external data required and primary focus of the task: explicit fact queries, implicit fact queries, interpretable rationale queries, and hidden rationale queries.

RAG

Anti-jamming Transmission of Downlink Cell Free Millimeter-Wave MIMO System

no code implementations20 Sep 2024 Zilong Wang, Cheng Zhang, Changwei Zhang, Yongming Huang

In this letter, the maximization of resistible jamming power is studied for multi-user downlink millimeter-wave cell-free multiple-input-multiple-output (CF-MIMO) systems.

Fairness

EnJa: Ensemble Jailbreak on Large Language Models

no code implementations7 Aug 2024 Jiahao Zhang, Zilong Wang, Ruofan Wang, Xingjun Ma, Yu-Gang Jiang

As Large Language Models (LLMs) are increasingly being deployed in safety-critical applications, their vulnerability to potential jailbreaks -- malicious prompts that can disable the safety mechanism of LLMs -- has attracted growing research attention.

Safety Alignment

Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

no code implementations11 Jul 2024 Zilong Wang, Zifeng Wang, Long Le, Huaixiu Steven Zheng, Swaroop Mishra, Vincent Perot, Yuwei Zhang, Anush Mattapalli, Ankur Taly, Jingbo Shang, Chen-Yu Lee, Tomas Pfister

Retrieval augmented generation (RAG) combines the generative abilities of large language models (LLMs) with external knowledge sources to provide more accurate and up-to-date responses.

ARC RAG +2

ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images

2 code implementations20 Jun 2024 Chen Liu, Ke Xu, Liangbo L. Shen, Guillaume Huguet, Zilong Wang, Alexander Tong, Danilo Bzdok, Jay Stewart, Jay C. Wang, Lucian V. Del Priore, Smita Krishnaswamy

We validate ImageFlowNet on three longitudinal medical image datasets depicting progression in geographic atrophy, multiple sclerosis, and glioblastoma, demonstrating its ability to effectively forecast disease progression and outperform existing methods.

Decision Making Medical Image Analysis +3

LLM-RadJudge: Achieving Radiologist-Level Evaluation for X-Ray Report Generation

no code implementations1 Apr 2024 Zilong Wang, Xufang Luo, Xinyang Jiang, Dongsheng Li, Lili Qiu

This study proposes a novel evaluation framework using large language models (LLMs) to compare radiology reports for assessment.

Knowledge Distillation

MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction Tasks

1 code implementation30 Mar 2024 Letian Peng, Zilong Wang, Feng Yao, Zihan Wang, Jingbo Shang

We construct the distillation dataset via sampling sentences from language model pre-training datasets (e. g., OpenWebText in our implementation) and prompting an LLM to identify the typed spans of "important information".

Language Modeling Language Modelling +3

DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering

no code implementations30 Mar 2024 Alex Nguyen, Zilong Wang, Jingbo Shang, Dheeraj Mekala

The application of natural language processing models to PDF documents is pivotal for various business applications yet the challenge of training models for this purpose persists in businesses due to specific hurdles.

Privacy Preserving Question Answering

ReSynthDetect: A Fundus Anomaly Detection Network with Reconstruction and Synthetic Features

no code implementations27 Dec 2023 Jingqi Niu, Qinji Yu, Shiwen Dong, Zilong Wang, Kang Dang, Xiaowei Ding

Detecting anomalies in fundus images through unsupervised methods is a challenging task due to the similarity between normal and abnormal tissues, as well as their indistinct boundaries.

Anomaly Detection Image Reconstruction

Small Area Estimation of Case Growths for Timely COVID-19 Outbreak Detection

1 code implementation7 Dec 2023 Zhaowei She, Zilong Wang, Jagpreet Chhatwal, Turgay Ayer

Furthermore, we conducted a case study based on outbreak case data from the state of Colorado and showed that the timely detection of outbreaks could have been improved by up to 224% using TLGRF when compared to the decisions made by Colorado's Department of Health and Environment (CDPHE).

Transfer Learning

Large Language Model based Long-tail Query Rewriting in Taobao Search

1 code implementation7 Nov 2023 Wenjun Peng, Guiyang Li, Yue Jiang, Zilong Wang, Dan Ou, Xiaoyi Zeng, Derong Xu, Tong Xu, Enhong Chen

In the realm of e-commerce search, the significance of semantic matching cannot be overstated, as it directly impacts both user experience and company revenue.

Contrastive Learning Language Modeling +3

EmojiLM: Modeling the New Emoji Language

1 code implementation3 Nov 2023 Letian Peng, Zilong Wang, Hang Liu, Zihan Wang, Jingbo Shang

With the rapid development of the internet, online social media welcomes people with different backgrounds through its diverse content.

Language Modeling Language Modelling +1

PAGE: Equilibrate Personalization and Generalization in Federated Learning

no code implementations13 Oct 2023 Qian Chen, Zilong Wang, Jiaqi Hu, Haonan Yan, Jianying Zhou, Xiaodong Lin

Federated learning (FL) is becoming a major driving force behind machine learning as a service, where customers (clients) collaboratively benefit from shared local updates under the orchestration of the service provider (server).

Federated Learning

LMDX: Language Model-based Document Information Extraction and Localization

no code implementations19 Sep 2023 Vincent Perot, Kai Kang, Florian Luisier, Guolong Su, Xiaoyu Sun, Ramya Sree Boppana, Zilong Wang, Zifeng Wang, Jiaqi Mu, Hao Zhang, Chen-Yu Lee, Nan Hua

The main obstacles to adopting LLMs for this task include the absence of layout encoding within LLMs, which is critical for high quality extraction, and the lack of a grounding mechanism to localize the predicted entities within the document.

Language Modeling Language Modelling

Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation

1 code implementation20 Aug 2023 Li Zhong, Zilong Wang

Existing code evaluation benchmark and datasets focus on crafting small tasks such as programming questions in coding interviews, which however deviates from the problem that developers would ask LLM for real-world coding help.

Code Generation Language Modeling +2

Towards Few-shot Entity Recognition in Document Images: A Graph Neural Network Approach Robust to Image Manipulation

1 code implementation24 May 2023 Prashant Krishnan, Zilong Wang, Yangkun Wang, Jingbo Shang

Recent advances of incorporating layout information, typically bounding box coordinates, into pre-trained language models have achieved significant performance in entity recognition from document images.

Graph Neural Network Image Manipulation +3

A Computational Model of Children's Learning and Use of Probabilities Across Different Ages

no code implementations6 May 2023 Zilong Wang, Thomas R. Shultz, Ardvan S. Nobandegani

Recent empirical work has shown that human children are adept at learning and reasoning with probabilities.

Delving into E-Commerce Product Retrieval with Vision-Language Pre-training

no code implementations10 Apr 2023 Xiaoyang Zheng, Fuyu Lv, Zilong Wang, Qingwen Liu, Xiaoyi Zeng

E-commerce search engines comprise a retrieval phase and a ranking phase, where the first one returns a candidate product set given user queries.

Contrastive Learning Retrieval

FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement

no code implementations8 Apr 2023 Xiaonan Nie, Xupeng Miao, Zilong Wang, Zichao Yang, Jilong Xue, Lingxiao Ma, Gang Cao, Bin Cui

We first present an empirical analysis on the problems and opportunities of training MoE models, which motivates us to overcome the routing imbalance and fluctuation problems by a dynamic expert management and device placement mechanism.

Scheduling

MAKE: Vision-Language Pre-training based Product Retrieval in Taobao Search

no code implementations30 Jan 2023 Xiaoyang Zheng, Zilong Wang, Ke Xu, Sen Li, Tao Zhuang, Qingwen Liu, Xiaoyi Zeng

Given a user query, the retrieval phase returns a subset of candidate products for the following ranking phase.

Retrieval

Improved Differential-neural Cryptanalysis for Round-reduced Simeck32/64

no code implementations27 Jan 2023 Liu Zhang, Jinyu Lu, Zilong Wang, Chao Li

Inspired by this framework, we develop the Inception neural network that is compatible with the round function of Simeck to improve the accuracy of the neural distinguishers, thus improving the accuracy of (9-12)-round neural distinguishers for Simeck32/64.

Cryptanalysis

Explaining Adversarial Robustness of Neural Networks from Clustering Effect Perspective

1 code implementation ICCV 2023 Yulin Jin, XiaoYu Zhang, Jian Lou, Xu Ma, Zilong Wang, Xiaofeng Chen

The experimental evaluations manifest the superiority of SAT over other state-of-the-art AT mechanisms in defending against adversarial attacks against both output and intermediate layers.

Adversarial Attack Adversarial Robustness +1

2D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraints

no code implementations5 Dec 2022 Zhangjian Ji, Zilong Wang, Ming Zhang, Yapeng Chen, Yuhua Qian

Recently, human pose estimation mainly focuses on how to design a more effective and better deep network structure as human features extractor, and most designed feature extraction networks only introduce the position of each anatomical keypoint to guide their training process.

2D Human Pose Estimation Pose Estimation

MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding

no code implementations27 Nov 2022 Zilong Wang, Jiuxiang Gu, Chris Tensmeyer, Nikolaos Barmpalios, Ani Nenkova, Tong Sun, Jingbo Shang, Vlad I. Morariu

In contrast, region-level models attempt to encode regions corresponding to paragraphs or text blocks into a single embedding, but they perform worse with additional word-level features.

VRDU: A Benchmark for Visually-rich Document Understanding

no code implementations15 Nov 2022 Zilong Wang, Yichao Zhou, Wei Wei, Chen-Yu Lee, Sandeep Tata

Understanding visually-rich business documents to extract structured data and automate business workflows has been receiving attention both in academia and industry.

document understanding

A Neural Model of Number Comparison with Surprisingly Robust Generalization

no code implementations13 Oct 2022 Thomas R. Shultz, Ardavan S. Nobandegani, Zilong Wang

We propose a relatively simple computational neural-network model of number comparison.

Tutel: Adaptive Mixture-of-Experts at Scale

2 code implementations7 Jun 2022 Changho Hwang, Wei Cui, Yifan Xiong, Ziyue Yang, Ze Liu, Han Hu, Zilong Wang, Rafael Salas, Jithin Jose, Prabhat Ram, Joe Chau, Peng Cheng, Fan Yang, Mao Yang, Yongqiang Xiong

On efficiency, Flex accelerates SwinV2-MoE, achieving up to 1. 55x and 2. 11x speedup in training and inference over Fairseq, respectively.

Object Detection

Formulating Few-shot Fine-tuning Towards Language Model Pre-training: A Pilot Study on Named Entity Recognition

1 code implementation24 May 2022 Zihan Wang, Kewen Zhao, Zilong Wang, Jingbo Shang

Fine-tuning pre-trained language models has recently become a common practice in building NLP models for various tasks, especially few-shot tasks.

Few-shot NER Language Modeling +3

Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework

1 code implementation Findings (ACL) 2022 Zilong Wang, Jingbo Shang

To overcome the data limitation, we propose to leverage the label surface names to better inform the model of the target entity type semantics and also embed the labels into the spatial embedding space to capture the spatial correspondence between regions and labels.

A Note on "Optimum Sets of Interference-Free Sequences With Zero Autocorrelation Zone"

no code implementations28 Feb 2022 Qiping Fang, Zilong Wang

In this paper, a simple construction of interference-free zero correlation zone (IF-ZCZ) sequence sets is proposed by well designed finite Zak transform lattice tessellation.

Symbolic AI for XAI: Evaluating LFIT Inductive Programming for Fair and Explainable Automatic Recruitment

no code implementations1 Dec 2020 Alfonso Ortega, Julian Fierrez, Aythami Morales, Zilong Wang, Tony Ribeiro

Machine learning methods are growing in relevance for biometrics and personal information processing in domains such as forensics, e-health, recruitment, and e-learning.

BIG-bench Machine Learning Explainable Artificial Intelligence (XAI) +1

Estimating County-Level COVID-19 Exponential Growth Rates Using Generalized Random Forests

1 code implementation31 Oct 2020 Zhaowei She, Zilong Wang, Turgay Ayer, Asmae Toumi, Jagpreet Chhatwal

Rapid and accurate detection of community outbreaks is critical to address the threat of resurgent waves of COVID-19.

TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis

no code implementations7 Sep 2020 Zilong Wang, Zhaohong Wan, Xiaojun Wan

Enlightened by recent success of Transformer in the area of machine translation, we propose a new fusion method, TransModality, to address the task of multimodal sentiment analysis.

 Ranked #1 on Multimodal Sentiment Analysis on CMU-MOSI (F1-score (Weighted) metric)

Machine Translation Multimodal Sentiment Analysis +1

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