Ping Li ( Alexander, Anderson, Arthur, Adeline)

Co-Founder and CEO, VecML Inc. ( Youtube LinkedIn)

pingli98@gmail.com

Awards

ONR-YIP, Young Investigator Award from the Office of Naval Research
AFOSR-YIP, Young Investigator Award from the Air Force Office of Scientific Research
Best Papers, Best Student Papers, Best Paper Hnorable mentiones, from NeurIPS, KDD, SIGIR, ASONAM, etc.

Publications

Generative AI Models (also see NLP and KG for papers relavant to generative AI models) 生成模型

Likelihood-Based Generative Radiance Field with Latent Space Energy-Based Model for 3D-Aware Disentangled Image Representation, AISTATS 2023. pdf
CoopInit: Initializing Generative Adversarial Networks via Cooperative Learning, AAAI 2023. pdf
A Tale of Two Latent Flows: Learning Latent Space Normalizing Flow with Short-run Langevin Flow for Approximate Inference, AAAI 2023. pdf
Learning Latent Structural Relations with Message Passing Prior, WACV 2023. pdf
A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model, ICLR 2022. pdf
Degenerate Swin to Win: Plain Window-based Transformer without Sophisticated Operations, Preprint 2022. pdf
Flow-based Perturbation for Cause-effect Inference, CIKM 2022. pdf
Variational Flow Graphical Model, KDD 2022. pdf
Causal Effect Prediction with Flow-based Inference, ICDM 2022. pdf
Learning Energy-Based Model with Variational Auto-Encoder as Amortized Sampler, AAAI 2021. pdf
Patchwise Generative ConvNet: Training Energy-Based Models from a Single Natural Image for Internal Learning, CVPR 2021. pdf
Learning Deep Latent Variable Models by Short-Run MCMC Inference with Optimal Transport Correction, CVPR 2021. pdf
Learning Energy-Based Generative Models via Coarse-to-Fine Expanding and Sampling, ICLR 2021. pdf
Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction, NeurIPS 2021. pdf
Causal Discovery with Flow-based Conditional Density Estimation, ICDM 2021. pdf
Estimate the Implicit Likelihoods of GANs with Application to Anomaly Detection, WWW 2020. pdf
Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation, AAAI 2020. pdf
Multi-Agent Discussion Mechanism for Natural Language Generation, AAAI 2019. pdf
Graph to Graph: a Topology Aware Approach for Graph Structures Learning and Generation, AISTATS 2019. pdf
On Random Deep Weight-Tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, and Implications to Training, ICLR 2019. pdf

Natural Language Processing (NLP), Cross-Modal, Cross-Language, Vision + NLP. (Also see related papers in Ads and Knowledge Graphs) 自然语言，跨模态，多模态

A Semi-Autoregressive Graph Generative Model for Dependency Graph Parsing, ACL 2023 (Findings). pdf
Denoising Enhanced Distantly Supervised Ultrafine Entity Typing, ACL 2023 (Findings). pdf
Learning to Selectively Learn for Weakly Supervised Paraphrase Generation with Model-based Reinforcement Learning, NAACL 2022. pdf
PromptGen: Automatically Generate Prompts using Generative Models, NAACL 2022 (Findings). pdf
Cross-Lingual Cross-Modal Consolidation for Effective Multilingual Video Corpus Moment Retrieval, NAACL 2022 (Findings). pdf
Cross-Probe BERT for Fast Cross-Modal Search, SIGIR 2022. pdf
Continual Learning for Natural Language Generations with Transformer Calibration, CoNLL 2022. pdf
Texture BERT for Cross-modal Texture Image Retrieval, CIKM 2022. pdf
U-BERT for Fast and Scalable Text-Image Retrieval, ICTIR 2022. pdf
Cross-lingual Language Model Pretraining for Retrieval, WWW 2021. pdf
Cross-lingual Cross-modal Pretraining for Multimodal Retrieval, NAACL 2021. pdf
Cross-Lingual Unsupervised Sentiment Classification with Multi-View Transfer Learning, ACL 2020. pdf
Inflate and Shrink: Enriching and Reducing Interactions for Fast Text-Image Retrieval, EMNLP 2021. pdf
A Deep Decomposable Model for Disentangling Syntax and Semantics in Sentence Representation, EMNLP 2021 (Findings). pdf
Hierarchical Multi-Task Word Embedding Learning for Synonym Prediction, KDD 2019. pdf
Coreference Aware Representation Learning for Neural Named Entity Recognition, IJCAI 2019. pdf
End-to-end Deep Reinforcement Learning Based Coreference Resolution, ACL 2019. pdf
Reinforced Product Metadata Selection for Helpfulness Assessment of Customer Reviews, EMNLP 2019. pdf

Advertising (Ads) 广告，搜广推

Media report: A Look at Baidu’s Industrial-Scale GPU Training Architecture. link
EGM: Enhanced Graph-based Model for Large-scale Video Advertisement Search, KDD 2022. pdf
Multi-scale Multi-modal Dictionary BERT For Effective Text-image Retrieval in Multimedia Advertising, CIKM 2022. pdf
Communication-Efficient TeraByte-Scale Model Training Framework for Online Advertising, BIGDATA 2022. pdf
Boost CTR Prediction for New Advertisements via Modeling Visual Content, BIGDATA 2022. pdf
FeatureBox: Feature Engineering on GPUs for Massive-Scale Ads Systems, BIGDATA 2022. pdf
Decomposing User-APP Graph into Subgraphs for Effective APP and User Embedding Learning. pdf
Tree-based Text-Vision BERT for Video Search in Baidu Video Advertising. pdf
Agile and Accurate CTR Prediction Model Training for Massive-Scale Online Advertising Systems, SIGMOD 2021. pdf
GemNN: Gating-Enhanced Multi-Task Neural Networks with Feature Interaction Learning for CTR Prediction, SIGIR 2021. pdf
Heterogeneous Attention Network for Effective and Efficient Cross-modal Retrieval, SIGIR 2021. pdf
TIRA in Baidu Image Advertising, ICDE 2021. pdf
Efficient Learning to Learn a Robust CTR Model for Web-scale Online Sponsored Search Advertising, CIKM 2021. pdf
Multi-modal Dictionary BERT for Cross-modal Video Search in Baidu Advertising, CIKM 2021. pdf
MixBERT for Multi-modal Matching in Image Advertising, CIKM 2021. pdf
Assorted Attention Network for Cross-Lingual Language-to-Vision Retrieval, CIKM 2021. pdf
Combo-Attention Network for Baidu Video Advertising, KDD 2020. pdf
Video Recommendation with Multi-gate Mixture of Experts Soft Actor Critic, SIGIR 2020. pdf
Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems, MLSys 2020. pdf
Sample Optimization For Display Advertising, CIKM 2020. pdf
AIBox: CTR Prediction Model Training on a Single Node, CIKM 2019. pdf
MOBIUS: Towards the Next Generation of Query-Ad Matching in Baidu’s Sponsored Search, KDD 2019. pdf

Input method editor (IME) 输入法

Improved Touch-screen Inputting Using Sequence-level Prediction Generation, WWW 2020. pdf
FastInput: Improving Input Efficiency on Mobile Devices, CIKM 2018. pdf

Knowledge graphs (KG) 知识图谱

OIE@OIA: an Adaptable and Efficient Open Information Extraction Framework, ACL 2022. pdf
SpaceE: Knowledge Graph Embedding by Relational Linear Transformation in the Entity Space, HT 2022. pdf
Explainable Concept Graph Completion by Bridging Open-DomainRelations and Concepts, SDM 2022. pdf
MQuadE: a Unified Model for Knowledge Fact Embedding, WWW 2021. pdf
ReadsRE: Retrieval-Augmented Distantly Supervised Relation Extraction, SIGIR 2021. pdf
Extracting Knowledge from Web Text with Monte Carlo Tree Search, WWW 2020. pdf
A Predicate-Function-Argument Annotation of Natural Language for Open-Domain Information eXpression, EMNLP 2020. pdf
Learning Interpretable Relationships between Entities, Relations and Concepts via Bayesian Structure Learning on Open Domain Facts, ACL 2020. pdf
Integration of Knowledge Graph Embedding into Topic Modeling with Hierarchical Dirichlet Process, NAACL 2019. pdf
Knowledge Graph Embedding Based Question Answering, WSDM 2019. pdf
Logician and Orator: Learning from the Duality between Language and Knowledge in Open Domain, EMNLP 2018. pdf
Logician: A Unified End-to-End Neural Approach for Open-Domain Information Extraction, WSDM 2018. pdf

Federated Learning, Deep Learning Tranining Algorithms 联邦学习、分布式训练、和深度学习训练算法

Sharper Analysis for Minibatch Stochastic Proximal Point Method: Stability, Smoothness, and Deviation, Journal of Machine Learning Research (JMLR), 2023. pdf
Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression, ICML 2023. pdf
On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond, NeurIPS 2022. pdf
Fed-LAMB: Layer-wise and Dimension-wise Locally Adaptive Federated Learning, UAI 2023. pdf
On Distributed Adaptive Optimization with Gradient Compression, ICLR 2022. pdf
On the Convergence of Decentralized Adaptive Gradient Methods, ACML 2022. pdf
An Optimistic Acceleration of AMSGrad for Nonconvex Optimization, ACML 2021. pdf
Toward Communication Efficient Adaptive Gradient Method, FODS 2020. pdf
Understanding and Detecting Convergence for Stochastic Gradient Descent with Momentum, BIGDATA 2020. pdf
On Convergence of Distributed Approximate Newton Methods: Globalization, Sharper Bounds and Beyond, Journal of Machine Learning Research 2020. pdf
Towards Better Generalization of Adaptive Gradient Methods, NeurIPS 2020. pdf

AI model security 模型安全

Defending Backdoor Attacks on Vision Transformer via Patch Processing, AAAI 2023. pdf
Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class, NeurIPS, 2022. pdf
Integrity Authentication in Tree Models, KDD 2022. pdf
Identification for Deep Neural Network: Simply Adjusting Few Weights!, ICDE 2022. pdf
DeepAuth: A DNN Authentication Framework by Model-Unique and Fragile ature Embedding, AAAI 2022. pdf
Backdoor Attack with Imperceptible Input and Latent Modification, NeurIPS 2021. pdf
LIRA: Learnable, Imperceptible and Robust Backdoor Attacks, ICCV 2021. pdf
Robust Watermarking for Deep Neural Networks via Bi-level Optimization, ICCV 2021. pdf

A/B testing

A/B Testing in Network Data with Covariate-Adaptive Randomization, ICML 2023. pdf
A New and Unified Family of Covariate Adaptive Randomization Procedures and Their Properties, JASA 2022. pdf
Adaptive A/B Test on Networks with Cluster Structures, AISTATS 2022. pdf
Adaptive Randomization in Network Data, Eletronic Journal of Statistics 2024. pdf