Ding Zhao

发表

Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method

Wenhao Ding, Minjun Xu, Ding Zhao, 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Combining Reachability Analysis and Importance Sampling for Accelerated Evaluation of Highway Automated Vehicles at Pedestrian Crossing

Ding Zhao, Huei Peng, Xinpeng Wang, 2020 .

On the Robustness of Safe Reinforcement Learning under Observational Perturbations

Jie Tan, Bo Li, Ding Zhao, 2022, ArXiv.

Prompting Decision Transformer for Few-Shot Policy Generalization

J. Tenenbaum, Yuchen Lu, Shun Zhang, 2022, ICML.

Semantically Adversarial Driving Scenario Generation with Explicit Knowledge Integration

Kim Ji Eun, Wenhao Ding, Ding Zhao, 2022 .

Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning

Wenhao Ding, Ding Zhao, Bo Li, 2022, ArXiv.

Privacy of Autonomous Vehicles: Risks, Protection Methods, and Future Directions

Chulin Xie, Diange Yang, Ding Zhao, 2022, ArXiv.

Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training

Ding Zhao, Peide Huang, Mengdi Xu, 2022, IJCAI.

GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction

Bo Li, Ding Zhao, Jielin Qiu, 2022, MLHC.

CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generation

Wenhao Ding, Ding Zhao, Hao-ming Lin, 2021, CoRL.

Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability

Wenhao Ding, Ding Zhao, Peide Huang, 2022, ArXiv.

Robustness Certification of Visual Perception Models via Camera Motion Smoothing

Linyi Li, Ding Zhao, Zuxin Liu, 2022, 2210.04625.

Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment

Bo Li, Hailin Jin, Trung Bui, 2022, ArXiv.

Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning

Wenhao Ding, Ding Zhao, Bo Li, 2022, ArXiv.

Over-Conservativeness of Variance-Based Efficiency Criteria and Probabilistic Efficiency in Rare-Event Simulation

H. Lam, Ding Zhao, Yuanlu Bai, 2021, 2110.12573.

CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing pdf

Yevgeniy Vorobeychik, Ding Zhao, Linyi Li, 2021, ICLR.

Robustness Certification of Visual Perception Models via Camera Motion Smoothing

Linyi Li, Ding Zhao, Zuxin Liu, 2022, CoRL.

Federated Pruning: Improving Neural Network Efficiency with Federated Learning

Li Xiong, Rongmei Lin, Yonghui Xiao, 2022, INTERSPEECH.

Continual Reinforcement Learning with Group Symmetries

Ding Zhao, K. Oguchi, Yongkang Liu, 2022, ArXiv.

Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling

H. Lam, Fengpei Li, Ding Zhao, 2021, 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Constrained Variational Policy Optimization for Safe Reinforcement Learning

Zhiwei Steven Wu, Bo Li, Ding Zhao, 2022, ICML.

Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?

Ding Zhao, Jiacheng Zhu, Emerson Liu, 2023, 2301.09017.

Delay-Aware Model-Based Reinforcement Learning for Continuous Control

Liang Li, Ding Zhao, Mengdi Xu, 2020, Neurocomputing.

Delay-Aware Multi-Agent Reinforcement Learning pdf

Baiming Chen, Mengdi Xu, Zuxin Liu, 2020, ArXiv.

Delay-Aware Multi-Agent Reinforcement Learning

Baiming Chen, Mengdi Xu, Zuxin Liu, 2020, ArXiv.

COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

K. Kenthapadi, B. Kailkhura, Linyi Li, 2022, ICLR.

CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing

Bo Li, Linyi Li, Ding Zhao, 2021, ICLR.

Semantically Controllable Scene Generation with Guidance of Explicit Knowledge pdf

Wenhao Ding, Ding Zhao, Bo Li, 2021, ArXiv.

Certifiable Deep Importance Sampling for Rare-Event Simulation of Black-Box Systems

Ding Zhao, Henry Lam, Mansur Arief, 2021, 2111.02204.

Deep Probabilistic Accelerated Evaluation: A Robust Certifiable Rare-Event Simulation Methodology for Black-Box Safety-Critical Systems

Guru Koushik Senthil Kumar, H. Lam, Mansur Arief, 2021, AISTATS.

Deep Probabilistic Accelerated Evaluation: A Certifiable Rare-Event Simulation Methodology for Black-Box Autonomy pdf

Wenhao Ding, Ding Zhao, Henry Lam, 2020, ArXiv.

Active Learning for Risk-Sensitive Inverse Reinforcement Learning pdf

Wenshuo Wang, Ding Zhao, Rui Chen, 2019, ArXiv.

Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning

Wenhao Ding, Ding Zhao, Bo Li, 2022, ArXiv.

Safe Model-based Reinforcement Learning with Robust Cross-Entropy Method pdf

Hongyi Zhou, Baiming Chen, Zuxin Liu, 2020, ArXiv.

Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation

Ding Zhao, Peide Huang, Laixi Shi, 2022, NeurIPS.

Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables

Bo Li, H. Lam, Visak C. V. Kumar, 2022, AISTATS.

GOATS: Goal Sampling Adaptation for Scooping with Curriculum Reinforcement Learning

Ding Zhao, Jiacheng Zhu, Yaru Niu, 2023, ArXiv.

Robust Unsupervised Learning of Temporal Dynamic Interactions pdf

Ding Zhao, Aritra Guha, Jiacheng Zhu, 2020, ArXiv.

Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes pdf

Wenhao Ding, Baiming Chen, Mengdi Xu, 2020, NeurIPS.

Shallow-Fusion End-to-End Contextual Biasing

Tara N. Sainath, Ding Zhao, Bo Li, 2019, INTERSPEECH.

A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality and Latency

Tara N. Sainath, Z. Chen, Yonghui Wu, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Dynamic Sparsity Neural Networks for Automatic Speech Recognition pdf

Ding Zhao, Jiahui Yu, Ruoming Pang, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles

Wenhao Ding, Ding Zhao, Yi He, 2022, NeurIPS.

Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation

Wenhao Ding, Ding Zhao, Bo Li, 2020, IEEE Robotics and Automation Letters.

Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method pdf

Wenhao Ding, Ding Zhao, Minjun Xu, 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Recurrent Attentive Neural Process for Sequential Data pdf

Wenshuo Wang, Ding Zhao, Jiacheng Zhu, 2019, ArXiv.

On the Robustness of Safe Reinforcement Learning under Observational Perturbations

Jie Tan, Bo Li, Ding Zhao, 2022, ICLR.

Multi-Vehicle Interaction Scenarios Generation with Interpretable Traffic Primitives and Gaussian Process Regression

Wenshuo Wang, Ding Zhao, Weiyang Zhang, 2019, 2020 IEEE Intelligent Vehicles Symposium (IV).

A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes

Tara N. Sainath, Rohit Prabhavalkar, R. Panigrahy, 2022, INTERSPEECH.

CMTS: A Conditional Multiple Trajectory Synthesizer for Generating Safety-Critical Driving Scenarios

Wenhao Ding, Mengdi Xu, Ding Zhao, 2019, 2020 IEEE International Conference on Robotics and Automation (ICRA).

Density-Adaptive Sampling for Heterogeneous Point Cloud Object Segmentation in Autonomous Vehicle Applications

Manoj Bhat, Ding Zhao, Ulf G. Indahl, 2019, CVPR Workshops.

A Versatile Approach to Evaluating and Testing Automated Vehicles based on Kernel Methods

Yaohui Guo, Ding Zhao, Zhiyuan Huang, 2017, 2018 Annual American Control Conference (ACC).

Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?

Ding Zhao, Jiacheng Zhu, W. Han, 2023, FINDINGS.

Hyper-Decision Transformer for Efficient Online Policy Adaptation

Yuchen Lu, Ding Zhao, Chuang Gan, 2023, ICLR.

Improving Perception via Sensor Placement: Designing Multi-LiDAR Systems for Autonomous Vehicles

Ding Zhao, Zuxin Liu, Akhil Agnihotri, 2021, ArXiv.

Interpolation for Robust Learning: Data Augmentation on Geodesics

X. Nguyen, Aritra Guha, Bo Li, 2023, ArXiv.

MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments pdf

Hongyi Zhou, Baiming Chen, Zuxin Liu, 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Crash Avoidance Systems-Safety Evaluation of an Important Class of Electronic Control Systems

David J. LeBlanc, Shan Bao, Ding Zhao, 2019 .

Cardiac Disease Diagnosis on Imbalanced Electrocardiography Data Through Optimal Transport Augmentation

Ding Zhao, Peide Huang, Jiacheng Zhu, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Functional optimal transport: map estimation and domain adaptation for functional data

X. Nguyen, Aritra Guha, Ding Zhao, 2021, 2102.03895.

Highway Exiting Planner for Automated Vehicles Using Reinforcement Learning

Ding Zhao, Shaobing Xu, Huei Peng, 2020, IEEE Transactions on Intelligent Transportation Systems.

How to Evaluate Proving Grounds for Self-Driving? A Quantitative Approach

Ding Zhao, Mansur Arief, Rui Chen, 2019, IEEE Transactions on Intelligent Transportation Systems.

How to Evaluate Self-Driving Testing Ground? A Quantitative Approach

Ding Zhao, Rui Chen, Weiyang Zhang, 2019 .

Continual Vision-based Reinforcement Learning with Group Symmetries

Ding Zhao, K. Oguchi, Yongkang Liu, 2022, CoRL.

Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning

Wenhao Ding, Ding Zhao, Bo Li, 2022, NeurIPS.

Your Room is not Private: Gradient Inversion Attack for Deep Q-Learning

Wenhao Ding, Ding Zhao, Miao Li, 2023, ArXiv.

Personalized Keyphrase Detection using Speaker and Environment Information pdf

Ian McGraw, Arun Narayanan, Ding Zhao, 2021, Interspeech.

MHMS: Multimodal Hierarchical Multimedia Summarization

Bo Li, Hailin Jin, Trung Bui, 2022, ArXiv.

Context-Aware Safe Reinforcement Learning for Non-Stationary Environments pdf

Wenhao Ding, Baiming Chen, Mengdi Xu, 2021, 2021 IEEE International Conference on Robotics and Automation (ICRA).

Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics

X. Nguyen, Aritra Guha, Bo Li, 2023, ICML.

An Empirical Exploration of Cross-domain Alignment between Language and Electroencephalogram

Bo Li, Ding Zhao, Jiacheng Zhu, 2022, ArXiv.

PhysioMTL: Personalizing Physiological Patterns using Optimal Transport Multi-Task Regression

X. Nguyen, Bo Li, Ding Zhao, 2022, CHIL.

Functional optimal transport: map estimation and domain adaptation for functional data

X. Nguyen, Aritra Guha, Ding Zhao, 2021, 2102.03895.

Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation

Yuejie Chi, Wenhao Ding, Ding Zhao, 2023, ArXiv.

O N THE R OBUSTNESS OF S AFE R EINFORCEMENT L EARNING UNDER O BSERVATIONAL P ERTURBATIONS

Ding Zhao, Zuxin Liu, Zijian Guo, 2023 .

Towards Robust and Safe Reinforcement Learning with Benign Off-policy Data

Ding Zhao, Zuxin Liu, Hanjiang Hu, 2023, ICML.

Accelerated Policy Evaluation: Learning Adversarial Environments with Adaptive Importance Sampling pdf

Ding Zhao, Henry Lam, Xuewei Qi, 2021, ArXiv.

Rare-event Simulation for Neural Network and Random Forest Predictors pdf

Ding Zhao, Henry Lam, Zhiyuan Huang, 2020, ACM Trans. Model. Comput. Simul..

Datasets and Benchmarks for Offline Safe Reinforcement Learning

Jie Tan, Wenhao Yu, Tingnan Zhang, 2023, ArXiv.

The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation

Wei Tsang Ooi, B. Cottereau, Tianzhu Zhang, 2023, ArXiv.

Interpolation for Robust Learning: Data Augmentation on Geodesics

X. Nguyen, Aritra Guha, Bo Li, 2023, ArXiv.

Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation

Yuejie Chi, Wenhao Ding, Ding Zhao, 2023, NeurIPS.

GOATS: Goal Sampling Adaptation for Scooping with Curriculum Reinforcement Learning

Ding Zhao, Jiacheng Zhu, Yaru Niu, 2023, arXiv.org.

Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models

Tong Che, M. Pavone, Wenhao Ding, 2023, ICML.

SCCS: Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment

Bo Li, Hailin Jin, Trung Bui, 2023, ACL.

Semantically Adversarial Scenario Generation with Explicit Knowledge Guidance

Wenhao Ding, Ding Zhao, Hao-ming Lin, 2021, 2106.04066.

Accelerated Evaluation of Automated Vehicles in Lane Change Scenarios

Huei Peng, Shan Bao, David J. LeBlanc, 2015 .

CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generation

Wenhao Ding, Ding Zhao, Hao-ming Lin, 2021, CoRL.