Jiacheng Zhu

 
                    @misc{brelgabrielsson2024compress,
                      title={Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead},
                      author={Rickard Brüel-Gabrielsson and Jiacheng Zhu and Onkar Bhardwaj and Leshem Choshen and Kristjan Greenewald and Mikhail Yurochkin and Justin Solomon},
                      year={2024},
                      eprint={2407.00066},
                      archivePrefix={arXiv},
                      primaryClass={cs.DC}
                  }
                    

 
              @inproceedings{qiu2024mmsum,
                title={MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos},
                author={Qiu, Jielin and Zhu, Jiacheng and Han, William and Kumar, Aditesh and Mittal, Karthik and Jin, Claire and Yang, Zhengyuan and Li, Linjie and Wang, Jianfeng and Zhao, Ding and others},
                booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
                pages={21909--21921},
                year={2024}
              }
               

 
                   @article{zhu2024asymmetry,
                     title={Asymmetry in Low-Rank Adapters of Foundation Models}, 
                     author={Jiacheng Zhu and Kristjan Greenewald and Kimia Nadjahi and Haitz Sáez de Ocáriz Borde and Rickard Brüel Gabrielsson and Leshem Choshen and Marzyeh Ghassemi and Mikhail Yurochkin and Justin Solomon},
                     year={2024},
               }
                   

 
                 @misc{zhu2021functional,
                     title={Functional optimal transport: map estimation and domain adaptation for functional data},
                     author={Jiacheng Zhu and Aritra Guha and Dat Do and Mengdi Xu and XuanLong Nguyen and Ding Zhao},
                     year={2021},
                     eprint={2102.03895},
                     archivePrefix={arXiv},
                     primaryClass={stat.ML}
                 }
                 

 
                    @InProceedings{pmlr-v225-qiu23a,
                      title = 	 {Automated Cardiovascular Record Retrieval by Multimodal Learning between Electrocardiogram and Clinical Report},
                      author =       {Qiu, Jielin and Zhu, Jiacheng and Liu, Shiqi and Han, William and Zhang, Jingqi and Duan, Chaojing and Rosenberg, Michael A. and Liu, Emerson and Weber, Douglas and Zhao, Ding},
                      booktitle = 	 {Proceedings of the 3rd Machine Learning for Health Symposium},
                      pages = 	 {480--497},
                      year = 	 {2023},
                      editor = 	 {Hegselmann, Stefan and Parziale, Antonio and Shanmugam, Divya and Tang, Shengpu and Asiedu, Mercy Nyamewaa and Chang, Serina and Hartvigsen, Tom and Singh, Harvineet},
                      volume = 	 {225},
                      series = 	 {Proceedings of Machine Learning Research},
                      month = 	 {10 Dec},
                      publisher =    {PMLR},
                      pdf = 	 {https://proceedings.mlr.press/v225/qiu23a/qiu23a.pdf},
                      url = 	 {https://proceedings.mlr.press/v225/qiu23a.html},
                      abstract = 	 {Automated interpretation of electrocardiograms (ECG) has garnered significant attention with the advancements in machine learning methodologies. Despite the growing interest, most current studies focus solely on classification or regression tasks which overlook a crucial aspect of clinical cardio-disease diagnosis: the diagnostic report generated by experienced human clinicians. In this paper, we introduce a novel approach to ECG interpretation, leveraging recent breakthroughs in Large Language Models (LLMs) and Vision-Transformer (ViT) models. Rather than treating ECG diagnosis as a classification or regression task, we propose an alternative method of automatically identifying the most similar clinical cases based on the input ECG data. Also, since interpreting ECG as images is more affordable and accessible, we process ECG as encoded images and adopt a vision-language learning paradigm to jointly learn vision-language alignment between encoded ECG images and ECG diagnosis reports. Encoding ECG into images can result in an efficient ECG retrieval system, which will be highly practical and useful in clinical applications. More importantly, our findings could serve as a crucial resource for providing diagnostic services in underdevelopment regions.}
                    }
                  

 
            @inproceedings{
                anonymous2023constraintconditioned,
                title={Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning},
                author={Anonymous},
                booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
                year={2023},
                url={https://openreview.net/forum?id=FdtdjQpAwJ}
                }
             

 
              @InProceedings{pmlr-v202-zhu23i,
                  title = 	 {Interpolation for Robust Learning: Data Augmentation on {W}asserstein Geodesics},
                  author =       {Zhu, Jiacheng and Qiu, Jielin and Guha, Aritra and Yang, Zhuolin and Nguyen, Xuanlong and Li, Bo and Zhao, Ding},
                  booktitle = 	 {Proceedings of the 40th International Conference on Machine Learning},
                  pages = 	 {43129--43157},
                  year = 	 {2023},
                  editor = 	 {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan},
                  volume = 	 {202},
                  series = 	 {Proceedings of Machine Learning Research},
                  month = 	 {23--29 Jul},
                  publisher =    {PMLR},
                  pdf = 	 {https://proceedings.mlr.press/v202/zhu23i/zhu23i.pdf},
                  url = 	 {https://proceedings.mlr.press/v202/zhu23i.html},
                  abstract = 	 {We propose to study and promote the robustness of a model as per its performance on a continuous geodesic interpolation of subpopulations, e.g., a class of samples in a classification problem. Specifically, (1) we augment the data by finding the worst-case Wasserstein barycenter on the geodesic connecting subpopulation distributions. (2) we regularize the model for smoother performance on the continuous geodesic path connecting subpopulation distributions. (3) Additionally, we provide a theoretical guarantee of robustness improvement and investigate how the geodesic location and the sample size contribute, respectively. Experimental validations of the proposed strategy on four datasets including CIFAR-100 and ImageNet, establish the efficacy of our method, e.g., our method improves the baselines’ certifiable robustness on CIFAR10 upto 7.7%, with 16.8% on empirical robustness on CIFAR-100. Our work provides a new perspective of model robustness through the lens of Wasserstein geodesic-based interpolation with a practical off-the-shelf strategy that can be combined with existing robust training methods.}
              }  
              

 
                    @inproceedings{
                        huang2022curriculum,
                        title={Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation},
                        author={Peide Huang and Mengdi Xu and Jiacheng Zhu and Laixi Shi and Fei Fang and Ding Zhao},
                        booktitle={Advances in Neural Information Processing Systems},
                        editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
                        year={2022},
                        url={https://openreview.net/forum?id=_cFdPHRLuJ}
                        }
                    

 
                    @InProceedings{pmlr-v182-zhu22a,
                        title = 	 {GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction},
                        author =       {Zhu, Jiacheng and Qiu, Jielin and Yang, Zhuolin and Weber, Douglas and Rosenberg, Michael A. and Liu, Emerson and Li, Bo and Zhao, Ding},
                        booktitle = 	 {Proceedings of the 7th Machine Learning for Healthcare Conference},
                        pages = 	 {172--197},
                        year = 	 {2022},
                        editor = 	 {Lipton, Zachary and Ranganath, Rajesh and Sendak, Mark and Sjoding, Michael and Yeung, Serena},
                        volume = 	 {182},
                        series = 	 {Proceedings of Machine Learning Research},
                        month = 	 {05--06 Aug},
                        publisher =    {PMLR},
                        pdf = 	 {https://proceedings.mlr.press/v182/zhu22a/zhu22a.pdf},
                        url = 	 {https://proceedings.mlr.press/v182/zhu22a.html},
                        abstract = 	 {There has been an increased interest in applying deep neural networks to automatically interpret and analyze the 12-lead electrocardiogram (ECG). The current paradigms with machine learning methods are often limited by the amount of labeled data. This phenomenon is particularly problematic for clinically-relevant data, where labeling at scale can be time-consuming and costly in terms of the specialized expertise and human effort required. Moreover, deep learning classifiers may be vulnerable to adversarial examples and perturbations, which could have catastrophic consequences, for example, when applied in the context of medical treatment, clinical trials, or insurance claims. In this paper, we propose a physiologically-inspired data augmentation method to improve performance and increase the robustness of heart disease detection based on ECG signals. We obtain augmented samples by perturbing the data distribution towards other classes along the geodesic in Wasserstein space. To better utilize domain-specific knowledge, we design a ground metric that recognizes the difference between ECG signals based on physiologically determined features. Learning from 12-lead ECG signals, our model is able to distinguish five categories of cardiac conditions. Our results demonstrate improvements in accuracy and robustness, reflecting the effectiveness of our data augmentation method.}
                    }
                  

 
                    @InProceedings{pmlr-v174-zhu22a,
                        title = 	 {PhysioMTL: Personalizing Physiological Patterns using Optimal Transport Multi-Task Regression},
                        author =       {Zhu, Jiacheng and Darnell, Gregory and Kumar, Agni and Zhao, Ding and Li, Bo and Nguyen, Xuanlong and Ren, Shirley You},
                        booktitle = 	 {Proceedings of the Conference on Health, Inference, and Learning},
                        pages = 	 {354--374},
                        year = 	 {2022},
                        editor = 	 {Flores, Gerardo and Chen, George H and Pollard, Tom and Ho, Joyce C and Naumann, Tristan},
                        volume = 	 {174},
                        series = 	 {Proceedings of Machine Learning Research},
                        month = 	 {07--08 Apr},
                        publisher =    {PMLR},
                        pdf = 	 {https://proceedings.mlr.press/v174/zhu22a/zhu22a.pdf},
                        url = 	 {https://proceedings.mlr.press/v174/zhu22a.html},
                        abstract = 	 {Heart rate variability (HRV) is a practical and noninvasive measure of autonomic nervous system activity, which plays an essential role in cardiovascular health. However, using HRV to assess physiology status is challenging. Even in clinical settings, HRV is sensitive to acute stressors such as physical activity, mental stress, hydration, alcohol, and sleep. Wearable devices provide convenient HRV measurements, but the irregularity of measurements and uncaptured stressors can bias conventional analytical methods. To better interpret HRV measurements for downstream healthcare applications, we learn a personalized diurnal rhythm as an accurate physiological indicator for each individual. We develop Physiological Multitask-Learning (PhysioMTL) by harnessing Optimal Transport theory within a Multitask-learning (MTL) framework. The proposed method learns an individual-specific predictive model from heterogeneous observations, and enables estimation of an optimal transport map that yields a push forward operation onto the demographic features for each task. Our model outperforms competing MTL methodologies on unobserved predictive tasks for synthetic and two real-world datasets. Specifically, our method provides remarkable prediction results on unseen held-out subjects given only $20%$ of the subjects in real-world observational studies. Furthermore, our model enables a counterfactual engine that generates the effect of acute stressors and chronic conditions on HRV rhythms.}
                    }
                  

 
                    @article{xu2020task,
                        title={Task-agnostic online reinforcement learning with an infinite mixture of gaussian processes},
                        author={Xu, Mengdi and Ding, Wenhao and Zhu, Jiacheng and Liu, Zuxin and Chen, Baiming and Zhao, Ding},
                        journal={Advances in Neural Information Processing Systems},
                        volume={33},
                        pages={6429--6440},
                        year={2020}
                      }
                    

 
                @InProceedings{pmlr-v225-qiu23a,
                  title = 	 {Automated Cardiovascular Record Retrieval by Multimodal Learning between Electrocardiogram and Clinical Report},
                  author =       {Qiu, Jielin and Zhu, Jiacheng and Liu, Shiqi and Han, William and Zhang, Jingqi and Duan, Chaojing and Rosenberg, Michael A. and Liu, Emerson and Weber, Douglas and Zhao, Ding},
                  booktitle = 	 {Proceedings of the 3rd Machine Learning for Health Symposium},
                  pages = 	 {480--497},
                  year = 	 {2023},
                  editor = 	 {Hegselmann, Stefan and Parziale, Antonio and Shanmugam, Divya and Tang, Shengpu and Asiedu, Mercy Nyamewaa and Chang, Serina and Hartvigsen, Tom and Singh, Harvineet},
                  volume = 	 {225},
                  series = 	 {Proceedings of Machine Learning Research},
                  month = 	 {10 Dec},
                  publisher =    {PMLR},
                  pdf = 	 {https://proceedings.mlr.press/v225/qiu23a/qiu23a.pdf},
                  url = 	 {https://proceedings.mlr.press/v225/qiu23a.html},
                  abstract = 	 {Automated interpretation of electrocardiograms (ECG) has garnered significant attention with the advancements in machine learning methodologies. Despite the growing interest, most current studies focus solely on classification or regression tasks which overlook a crucial aspect of clinical cardio-disease diagnosis: the diagnostic report generated by experienced human clinicians. In this paper, we introduce a novel approach to ECG interpretation, leveraging recent breakthroughs in Large Language Models (LLMs) and Vision-Transformer (ViT) models. Rather than treating ECG diagnosis as a classification or regression task, we propose an alternative method of automatically identifying the most similar clinical cases based on the input ECG data. Also, since interpreting ECG as images is more affordable and accessible, we process ECG as encoded images and adopt a vision-language learning paradigm to jointly learn vision-language alignment between encoded ECG images and ECG diagnosis reports. Encoding ECG into images can result in an efficient ECG retrieval system, which will be highly practical and useful in clinical applications. More importantly, our findings could serve as a crucial resource for providing diagnostic services in underdevelopment regions.}
                }
              

 
            @inproceedings{qiu2023cardiac,
                title={Cardiac Disease Diagnosis on Imbalanced Electrocardiography Data Through Optimal Transport Augmentation},
                author={Qiu, Jielin and Zhu, Jiacheng and Xu, Mengdi and Huang, Peide and Rosenberg, Michael and Weber, Douglas and Liu, Emerson and Zhao, Ding},
                booktitle={ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
                pages={1--5},
                year={2023},
                organization={IEEE}
              }
             

 
                @inproceedings{qiu2023transfer,
                    title={Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?},
                    author={Qiu, Jielin and Han, William and Zhu, Jiacheng and Xu, Mengdi and Rosenberg, Michael and Liu, Emerson and Weber, Douglas and Zhao, Ding},
                    booktitle={Findings of the Association for Computational Linguistics: EACL 2023},
                    pages={442--453},
                    year={2023}
                }
                

 
                @InProceedings{pmlr-v182-zhu22a,
                    title = 	 {GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction},
                    author =       {Zhu, Jiacheng and Qiu, Jielin and Yang, Zhuolin and Weber, Douglas and Rosenberg, Michael A. and Liu, Emerson and Li, Bo and Zhao, Ding},
                    booktitle = 	 {Proceedings of the 7th Machine Learning for Healthcare Conference},
                    pages = 	 {172--197},
                    year = 	 {2022},
                    editor = 	 {Lipton, Zachary and Ranganath, Rajesh and Sendak, Mark and Sjoding, Michael and Yeung, Serena},
                    volume = 	 {182},
                    series = 	 {Proceedings of Machine Learning Research},
                    month = 	 {05--06 Aug},
                    publisher =    {PMLR},
                    pdf = 	 {https://proceedings.mlr.press/v182/zhu22a/zhu22a.pdf},
                    url = 	 {https://proceedings.mlr.press/v182/zhu22a.html},
                    abstract = 	 {There has been an increased interest in applying deep neural networks to automatically interpret and analyze the 12-lead electrocardiogram (ECG). The current paradigms with machine learning methods are often limited by the amount of labeled data. This phenomenon is particularly problematic for clinically-relevant data, where labeling at scale can be time-consuming and costly in terms of the specialized expertise and human effort required. Moreover, deep learning classifiers may be vulnerable to adversarial examples and perturbations, which could have catastrophic consequences, for example, when applied in the context of medical treatment, clinical trials, or insurance claims. In this paper, we propose a physiologically-inspired data augmentation method to improve performance and increase the robustness of heart disease detection based on ECG signals. We obtain augmented samples by perturbing the data distribution towards other classes along the geodesic in Wasserstein space. To better utilize domain-specific knowledge, we design a ground metric that recognizes the difference between ECG signals based on physiologically determined features. Learning from 12-lead ECG signals, our model is able to distinguish five categories of cardiac conditions. Our results demonstrate improvements in accuracy and robustness, reflecting the effectiveness of our data augmentation method.}
                }
              

 
                @InProceedings{pmlr-v174-zhu22a,
                    title = 	 {PhysioMTL: Personalizing Physiological Patterns using Optimal Transport Multi-Task Regression},
                    author =       {Zhu, Jiacheng and Darnell, Gregory and Kumar, Agni and Zhao, Ding and Li, Bo and Nguyen, Xuanlong and Ren, Shirley You},
                    booktitle = 	 {Proceedings of the Conference on Health, Inference, and Learning},
                    pages = 	 {354--374},
                    year = 	 {2022},
                    editor = 	 {Flores, Gerardo and Chen, George H and Pollard, Tom and Ho, Joyce C and Naumann, Tristan},
                    volume = 	 {174},
                    series = 	 {Proceedings of Machine Learning Research},
                    month = 	 {07--08 Apr},
                    publisher =    {PMLR},
                    pdf = 	 {https://proceedings.mlr.press/v174/zhu22a/zhu22a.pdf},
                    url = 	 {https://proceedings.mlr.press/v174/zhu22a.html},
                    abstract = 	 {Heart rate variability (HRV) is a practical and noninvasive measure of autonomic nervous system activity, which plays an essential role in cardiovascular health. However, using HRV to assess physiology status is challenging. Even in clinical settings, HRV is sensitive to acute stressors such as physical activity, mental stress, hydration, alcohol, and sleep. Wearable devices provide convenient HRV measurements, but the irregularity of measurements and uncaptured stressors can bias conventional analytical methods. To better interpret HRV measurements for downstream healthcare applications, we learn a personalized diurnal rhythm as an accurate physiological indicator for each individual. We develop Physiological Multitask-Learning (PhysioMTL) by harnessing Optimal Transport theory within a Multitask-learning (MTL) framework. The proposed method learns an individual-specific predictive model from heterogeneous observations, and enables estimation of an optimal transport map that yields a push forward operation onto the demographic features for each task. Our model outperforms competing MTL methodologies on unobserved predictive tasks for synthetic and two real-world datasets. Specifically, our method provides remarkable prediction results on unseen held-out subjects given only $20%$ of the subjects in real-world observational studies. Furthermore, our model enables a counterfactual engine that generates the effect of acute stressors and chronic conditions on HRV rhythms.}
                }
              

 
                    @inproceedings{dong2022re,
                        title={Re-vibe: Vibration-based indoor person re-identification through cross-structure optimal transport},
                        author={Dong, Yiwen and Zhu, Jiacheng and Noh, Hae Young},
                        booktitle={Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation},
                        pages={348--352},
                        year={2022}
                    }
                

 
            @misc{niu2023goats,
                title={GOATS: Goal Sampling Adaptation for Scooping with Curriculum Reinforcement Learning},
                author={Yaru Niu and Shiyu Jin and Zeqing Zhang and Jiacheng Zhu and Ding Zhao and Liangjun Zhang},
                year={2023},
                eprint={2303.05193},
                archivePrefix={arXiv},
                primaryClass={cs.RO}
            }
             

 
                @InProceedings{pmlr-v205-hu23b,
                    title = 	 {Robustness Certification of Visual Perception Models via Camera Motion Smoothing},
                    author =       {Hu, Hanjiang and Liu, Zuxin and Li, Linyi and Zhu, Jiacheng and Zhao, Ding},
                    booktitle = 	 {Proceedings of The 6th Conference on Robot Learning},
                    pages = 	 {1309--1320},
                    year = 	 {2023},
                    editor = 	 {Liu, Karen and Kulic, Dana and Ichnowski, Jeff},
                    volume = 	 {205},
                    series = 	 {Proceedings of Machine Learning Research},
                    month = 	 {14--18 Dec},
                    publisher =    {PMLR},
                    pdf = 	 {https://proceedings.mlr.press/v205/hu23b/hu23b.pdf},
                    url = 	 {https://proceedings.mlr.press/v205/hu23b.html},
                    abstract = 	 {A vast literature shows that the learning-based visual perception model is sensitive to adversarial noises, but few works consider the robustness of robotic perception models under widely-existing camera motion perturbations. To this end, we study the robustness of the visual perception model under camera motion perturbations to investigate the influence of camera motion on robotic perception. Specifically, we propose a motion smoothing technique for arbitrary image classification models, whose robustness under camera motion perturbations could be certified. The proposed robustness certification framework based on camera motion smoothing provides effective and scalable robustness guarantees for visual perception modules so that they are applicable to wide robotic applications. As far as we are aware, this is the first work to provide robustness certification for the deep perception module against camera motions, which improves the trustworthiness of robotic perception. A realistic indoor robotic dataset with a dense point cloud map for the entire room, MetaRoom, is introduced for the challenging certifiable robust perception task. We conduct extensive experiments to validate the certification approach via motion smoothing against camera motion perturbations. Our framework guarantees the certified accuracy of 81.7% against camera translation perturbation along depth direction within -0.1m   0.1m. We also validate the effectiveness of our method on the real-world robot by conducting hardware experiments on the robotic arm with an eye-in-hand camera. The code is available at https://github.com/HanjiangHu/camera-motion-smoothing.}
                }
            

 
                @inproceedings{xu2022scalable,
                    title={Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling},
                    author={Xu, Mengdi and Huang, Peide and Li, Fengpei and Zhu, Jiacheng and Qi, Xuewei and Oguchi, Kentaro and Huang, Zhiyuan and Lam, Henry and Zhao, Ding},
                    booktitle={2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
                    pages={12919--12926},
                    year={2022},
                    organization={IEEE}
                  }
               

 
                @article{zhang2021spatiotemporal,
                    title={Spatiotemporal learning of multivehicle interaction patterns in lane-change scenarios},
                    author={Zhang, Chengyuan and Zhu, Jiacheng and Wang, Wenshuo and Xi, Junqiang},
                    journal={IEEE Transactions on Intelligent Transportation Systems},
                    volume={23},
                    number={7},
                    pages={6446--6459},
                    year={2021},
                    publisher={IEEE}
                  }
                

 
                @inproceedings{chen2021context,
                    title={Context-aware safe reinforcement learning for non-stationary environments},
                    author={Chen, Baiming and Liu, Zuxin and Zhu, Jiacheng and Xu, Mengdi and Ding, Wenhao and Li, Liang and Zhao, Ding},
                    booktitle={2021 IEEE International Conference on Robotics and Automation (ICRA)},
                    pages={10689--10695},
                    year={2021},
                    organization={IEEE}
                  }
                

 
                @inproceedings{zhu2018tempt,
                    title={A tempt to unify heterogeneous driving databases using traffic primitives},
                    author={Zhu, Jiacheng and Wang, Wenshuo and Zhao, Ding},
                    booktitle={2018 21st International Conference on Intelligent Transportation Systems (ITSC)},
                    pages={2052--2057},
                    year={2018},
                    organization={IEEE}
                  }
               

 
                @misc{brelgabrielsson2024compress,
                  title={Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead},
                  author={Rickard Brüel-Gabrielsson and Jiacheng Zhu and Onkar Bhardwaj and Leshem Choshen and Kristjan Greenewald and Mikhail Yurochkin and Justin Solomon},
                  year={2024},
                  eprint={2407.00066},
                  archivePrefix={arXiv},
                  primaryClass={cs.DC}
              }
                

 
              @inproceedings{qiu2024mmsum,
                title={MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos},
                author={Qiu, Jielin and Zhu, Jiacheng and Han, William and Kumar, Aditesh and Mittal, Karthik and Jin, Claire and Yang, Zhengyuan and Li, Linjie and Wang, Jianfeng and Zhao, Ding and others},
                booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
                pages={21909--21921},
                year={2024}
              }
               

 
                @article{zhu2024asymmetry,
                  title={Asymmetry in Low-Rank Adapters of Foundation Models}, 
                  author={Jiacheng Zhu and Kristjan Greenewald and Kimia Nadjahi and Haitz Sáez de Ocáriz Borde and Rickard Brüel Gabrielsson and Leshem Choshen and Marzyeh Ghassemi and Mikhail Yurochkin and Justin Solomon},
                  year={2024},
            }
                

 
             @misc{zhu2021functional,
                 title={Functional optimal transport: map estimation and domain adaptation for functional data},
                 author={Jiacheng Zhu and Aritra Guha and Dat Do and Mengdi Xu and XuanLong Nguyen and Ding Zhao},
                 year={2021},
                 eprint={2102.03895},
                 archivePrefix={arXiv},
                 primaryClass={stat.ML}
             }
             

 
                    @InProceedings{pmlr-v225-qiu23a,
                      title = 	 {Automated Cardiovascular Record Retrieval by Multimodal Learning between Electrocardiogram and Clinical Report},
                      author =       {Qiu, Jielin and Zhu, Jiacheng and Liu, Shiqi and Han, William and Zhang, Jingqi and Duan, Chaojing and Rosenberg, Michael A. and Liu, Emerson and Weber, Douglas and Zhao, Ding},
                      booktitle = 	 {Proceedings of the 3rd Machine Learning for Health Symposium},
                      pages = 	 {480--497},
                      year = 	 {2023},
                      editor = 	 {Hegselmann, Stefan and Parziale, Antonio and Shanmugam, Divya and Tang, Shengpu and Asiedu, Mercy Nyamewaa and Chang, Serina and Hartvigsen, Tom and Singh, Harvineet},
                      volume = 	 {225},
                      series = 	 {Proceedings of Machine Learning Research},
                      month = 	 {10 Dec},
                      publisher =    {PMLR},
                      pdf = 	 {https://proceedings.mlr.press/v225/qiu23a/qiu23a.pdf},
                      url = 	 {https://proceedings.mlr.press/v225/qiu23a.html},
                      abstract = 	 {Automated interpretation of electrocardiograms (ECG) has garnered significant attention with the advancements in machine learning methodologies. Despite the growing interest, most current studies focus solely on classification or regression tasks which overlook a crucial aspect of clinical cardio-disease diagnosis: the diagnostic report generated by experienced human clinicians. In this paper, we introduce a novel approach to ECG interpretation, leveraging recent breakthroughs in Large Language Models (LLMs) and Vision-Transformer (ViT) models. Rather than treating ECG diagnosis as a classification or regression task, we propose an alternative method of automatically identifying the most similar clinical cases based on the input ECG data. Also, since interpreting ECG as images is more affordable and accessible, we process ECG as encoded images and adopt a vision-language learning paradigm to jointly learn vision-language alignment between encoded ECG images and ECG diagnosis reports. Encoding ECG into images can result in an efficient ECG retrieval system, which will be highly practical and useful in clinical applications. More importantly, our findings could serve as a crucial resource for providing diagnostic services in underdevelopment regions.}
                    }
                  

 
            @inproceedings{
                anonymous2023constraintconditioned,
                title={Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning},
                author={Anonymous},
                booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
                year={2023},
                url={https://openreview.net/forum?id=FdtdjQpAwJ}
                }
             

 
            @misc{niu2023goats,
                title={GOATS: Goal Sampling Adaptation for Scooping with Curriculum Reinforcement Learning},
                author={Yaru Niu and Shiyu Jin and Zeqing Zhang and Jiacheng Zhu and Ding Zhao and Liangjun Zhang},
                year={2023},
                eprint={2303.05193},
                archivePrefix={arXiv},
                primaryClass={cs.RO}
            }
             

 
            @inproceedings{qiu-etal-2023-sccs,
                title = "{SCCS}: Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment",
                author = "Qiu, Jielin  and Zhu, Jiacheng  and
                  Xu, Mengdi  and Dernoncourt, Franck  and
                  Bui, Trung  and Wang, Zhaowen  and Li, Bo  and Zhao, Ding  and
                  Jin, Hailin",
                booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
                month = jul,
                year = "2023",
                address = "Toronto, Canada",
                publisher = "Association for Computational Linguistics",
                url = "https://aclanthology.org/2023.findings-acl.101",
                doi = "10.18653/v1/2023.findings-acl.101",
                pages = "1584--1601",
                abstract = "Multimedia summarization with multimodal output (MSMO) is a recently explored application in language grounding. It plays an essential role in real-world applications, i.e., automatically generating cover images and titles for news articles or providing introductions to online videos. However, existing methods extract features from the whole video and article and use fusion methods to select the representative one, thus usually ignoring the critical structure and varying semantics with video/document. In this work, we propose a Semantics-Consistent Cross-domain Summarization (SCCS) model based on optimal transport alignment with visual and textual segmentation. Our method first decomposes both videos and articles into segments in order to capture the structural semantics, and then follows a cross-domain alignment objective with optimal transport distance, which leverages multimodal interaction to match and select the visual and textual summary. We evaluated our method on three MSMO datasets, and achieved performance improvement by 8{\%} {\&} 6{\%} of textual and 6.6{\%} {\&}5.7{\%} of video summarization, respectively, which demonstrated the effectiveness of our method in producing high-quality multimodal summaries.",
            }
            
          

 
            @inproceedings{qiu2023cardiac,
                title={Cardiac Disease Diagnosis on Imbalanced Electrocardiography Data Through Optimal Transport Augmentation},
                author={Qiu, Jielin and Zhu, Jiacheng and Xu, Mengdi and Huang, Peide and Rosenberg, Michael and Weber, Douglas and Liu, Emerson and Zhao, Ding},
                booktitle={ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
                pages={1--5},
                year={2023},
                organization={IEEE}
              }
             

 
          @InProceedings{pmlr-v202-zhu23i,
              title = 	 {Interpolation for Robust Learning: Data Augmentation on {W}asserstein Geodesics},
              author =       {Zhu, Jiacheng and Qiu, Jielin and Guha, Aritra and Yang, Zhuolin and Nguyen, Xuanlong and Li, Bo and Zhao, Ding},
              booktitle = 	 {Proceedings of the 40th International Conference on Machine Learning},
              pages = 	 {43129--43157},
              year = 	 {2023},
              editor = 	 {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan},
              volume = 	 {202},
              series = 	 {Proceedings of Machine Learning Research},
              month = 	 {23--29 Jul},
              publisher =    {PMLR},
              pdf = 	 {https://proceedings.mlr.press/v202/zhu23i/zhu23i.pdf},
              url = 	 {https://proceedings.mlr.press/v202/zhu23i.html},
              abstract = 	 {We propose to study and promote the robustness of a model as per its performance on a continuous geodesic interpolation of subpopulations, e.g., a class of samples in a classification problem. Specifically, (1) we augment the data by finding the worst-case Wasserstein barycenter on the geodesic connecting subpopulation distributions. (2) we regularize the model for smoother performance on the continuous geodesic path connecting subpopulation distributions. (3) Additionally, we provide a theoretical guarantee of robustness improvement and investigate how the geodesic location and the sample size contribute, respectively. Experimental validations of the proposed strategy on four datasets including CIFAR-100 and ImageNet, establish the efficacy of our method, e.g., our method improves the baselines’ certifiable robustness on CIFAR10 upto 7.7%, with 16.8% on empirical robustness on CIFAR-100. Our work provides a new perspective of model robustness through the lens of Wasserstein geodesic-based interpolation with a practical off-the-shelf strategy that can be combined with existing robust training methods.}
          }  
          

 
                @inproceedings{qiu2023transfer,
                    title={Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?},
                    author={Qiu, Jielin and Han, William and Zhu, Jiacheng and Xu, Mengdi and Rosenberg, Michael and Liu, Emerson and Weber, Douglas and Zhao, Ding},
                    booktitle={Findings of the Association for Computational Linguistics: EACL 2023},
                    pages={442--453},
                    year={2023}
                }
                

 
                @inproceedings{
                    huang2022curriculum,
                    title={Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation},
                    author={Peide Huang and Mengdi Xu and Jiacheng Zhu and Laixi Shi and Fei Fang and Ding Zhao},
                    booktitle={Advances in Neural Information Processing Systems},
                    editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
                    year={2022},
                    url={https://openreview.net/forum?id=_cFdPHRLuJ}
                    }
                

 
                @InProceedings{pmlr-v182-zhu22a,
                    title = 	 {GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction},
                    author =       {Zhu, Jiacheng and Qiu, Jielin and Yang, Zhuolin and Weber, Douglas and Rosenberg, Michael A. and Liu, Emerson and Li, Bo and Zhao, Ding},
                    booktitle = 	 {Proceedings of the 7th Machine Learning for Healthcare Conference},
                    pages = 	 {172--197},
                    year = 	 {2022},
                    editor = 	 {Lipton, Zachary and Ranganath, Rajesh and Sendak, Mark and Sjoding, Michael and Yeung, Serena},
                    volume = 	 {182},
                    series = 	 {Proceedings of Machine Learning Research},
                    month = 	 {05--06 Aug},
                    publisher =    {PMLR},
                    pdf = 	 {https://proceedings.mlr.press/v182/zhu22a/zhu22a.pdf},
                    url = 	 {https://proceedings.mlr.press/v182/zhu22a.html},
                    abstract = 	 {There has been an increased interest in applying deep neural networks to automatically interpret and analyze the 12-lead electrocardiogram (ECG). The current paradigms with machine learning methods are often limited by the amount of labeled data. This phenomenon is particularly problematic for clinically-relevant data, where labeling at scale can be time-consuming and costly in terms of the specialized expertise and human effort required. Moreover, deep learning classifiers may be vulnerable to adversarial examples and perturbations, which could have catastrophic consequences, for example, when applied in the context of medical treatment, clinical trials, or insurance claims. In this paper, we propose a physiologically-inspired data augmentation method to improve performance and increase the robustness of heart disease detection based on ECG signals. We obtain augmented samples by perturbing the data distribution towards other classes along the geodesic in Wasserstein space. To better utilize domain-specific knowledge, we design a ground metric that recognizes the difference between ECG signals based on physiologically determined features. Learning from 12-lead ECG signals, our model is able to distinguish five categories of cardiac conditions. Our results demonstrate improvements in accuracy and robustness, reflecting the effectiveness of our data augmentation method.}
                }
              

 
                @InProceedings{pmlr-v174-zhu22a,
                    title = 	 {PhysioMTL: Personalizing Physiological Patterns using Optimal Transport Multi-Task Regression},
                    author =       {Zhu, Jiacheng and Darnell, Gregory and Kumar, Agni and Zhao, Ding and Li, Bo and Nguyen, Xuanlong and Ren, Shirley You},
                    booktitle = 	 {Proceedings of the Conference on Health, Inference, and Learning},
                    pages = 	 {354--374},
                    year = 	 {2022},
                    editor = 	 {Flores, Gerardo and Chen, George H and Pollard, Tom and Ho, Joyce C and Naumann, Tristan},
                    volume = 	 {174},
                    series = 	 {Proceedings of Machine Learning Research},
                    month = 	 {07--08 Apr},
                    publisher =    {PMLR},
                    pdf = 	 {https://proceedings.mlr.press/v174/zhu22a/zhu22a.pdf},
                    url = 	 {https://proceedings.mlr.press/v174/zhu22a.html},
                    abstract = 	 {Heart rate variability (HRV) is a practical and noninvasive measure of autonomic nervous system activity, which plays an essential role in cardiovascular health. However, using HRV to assess physiology status is challenging. Even in clinical settings, HRV is sensitive to acute stressors such as physical activity, mental stress, hydration, alcohol, and sleep. Wearable devices provide convenient HRV measurements, but the irregularity of measurements and uncaptured stressors can bias conventional analytical methods. To better interpret HRV measurements for downstream healthcare applications, we learn a personalized diurnal rhythm as an accurate physiological indicator for each individual. We develop Physiological Multitask-Learning (PhysioMTL) by harnessing Optimal Transport theory within a Multitask-learning (MTL) framework. The proposed method learns an individual-specific predictive model from heterogeneous observations, and enables estimation of an optimal transport map that yields a push forward operation onto the demographic features for each task. Our model outperforms competing MTL methodologies on unobserved predictive tasks for synthetic and two real-world datasets. Specifically, our method provides remarkable prediction results on unseen held-out subjects given only $20%$ of the subjects in real-world observational studies. Furthermore, our model enables a counterfactual engine that generates the effect of acute stressors and chronic conditions on HRV rhythms.}
                }
              

 
                @InProceedings{pmlr-v205-hu23b,
                    title = 	 {Robustness Certification of Visual Perception Models via Camera Motion Smoothing},
                    author =       {Hu, Hanjiang and Liu, Zuxin and Li, Linyi and Zhu, Jiacheng and Zhao, Ding},
                    booktitle = 	 {Proceedings of The 6th Conference on Robot Learning},
                    pages = 	 {1309--1320},
                    year = 	 {2023},
                    editor = 	 {Liu, Karen and Kulic, Dana and Ichnowski, Jeff},
                    volume = 	 {205},
                    series = 	 {Proceedings of Machine Learning Research},
                    month = 	 {14--18 Dec},
                    publisher =    {PMLR},
                    pdf = 	 {https://proceedings.mlr.press/v205/hu23b/hu23b.pdf},
                    url = 	 {https://proceedings.mlr.press/v205/hu23b.html},
                    abstract = 	 {A vast literature shows that the learning-based visual perception model is sensitive to adversarial noises, but few works consider the robustness of robotic perception models under widely-existing camera motion perturbations. To this end, we study the robustness of the visual perception model under camera motion perturbations to investigate the influence of camera motion on robotic perception. Specifically, we propose a motion smoothing technique for arbitrary image classification models, whose robustness under camera motion perturbations could be certified. The proposed robustness certification framework based on camera motion smoothing provides effective and scalable robustness guarantees for visual perception modules so that they are applicable to wide robotic applications. As far as we are aware, this is the first work to provide robustness certification for the deep perception module against camera motions, which improves the trustworthiness of robotic perception. A realistic indoor robotic dataset with a dense point cloud map for the entire room, MetaRoom, is introduced for the challenging certifiable robust perception task. We conduct extensive experiments to validate the certification approach via motion smoothing against camera motion perturbations. Our framework guarantees the certified accuracy of 81.7% against camera translation perturbation along depth direction within -0.1m   0.1m. We also validate the effectiveness of our method on the real-world robot by conducting hardware experiments on the robotic arm with an eye-in-hand camera. The code is available at https://github.com/HanjiangHu/camera-motion-smoothing.}
                }
            

 
                @inproceedings{dong2022re,
                    title={Re-vibe: Vibration-based indoor person re-identification through cross-structure optimal transport},
                    author={Dong, Yiwen and Zhu, Jiacheng and Noh, Hae Young},
                    booktitle={Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation},
                    pages={348--352},
                    year={2022}
                  }
               

 
                @inproceedings{xu2022scalable,
                    title={Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling},
                    author={Xu, Mengdi and Huang, Peide and Li, Fengpei and Zhu, Jiacheng and Qi, Xuewei and Oguchi, Kentaro and Huang, Zhiyuan and Lam, Henry and Zhao, Ding},
                    booktitle={2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
                    pages={12919--12926},
                    year={2022},
                    organization={IEEE}
                  }
               

 
                @article{zhang2021spatiotemporal,
                    title={Spatiotemporal learning of multivehicle interaction patterns in lane-change scenarios},
                    author={Zhang, Chengyuan and Zhu, Jiacheng and Wang, Wenshuo and Xi, Junqiang},
                    journal={IEEE Transactions on Intelligent Transportation Systems},
                    volume={23},
                    number={7},
                    pages={6446--6459},
                    year={2021},
                    publisher={IEEE}
                  }
                

 
                @inproceedings{chen2021context,
                    title={Context-aware safe reinforcement learning for non-stationary environments},
                    author={Chen, Baiming and Liu, Zuxin and Zhu, Jiacheng and Xu, Mengdi and Ding, Wenhao and Li, Liang and Zhao, Ding},
                    booktitle={2021 IEEE International Conference on Robotics and Automation (ICRA)},
                    pages={10689--10695},
                    year={2021},
                    organization={IEEE}
                  }
                

 
                @article{xu2020task,
                    title={Task-agnostic online reinforcement learning with an infinite mixture of gaussian processes},
                    author={Xu, Mengdi and Ding, Wenhao and Zhu, Jiacheng and Liu, Zuxin and Chen, Baiming and Zhao, Ding},
                    journal={Advances in Neural Information Processing Systems},
                    volume={33},
                    pages={6429--6440},
                    year={2020}
                  }
                

 
                @article{qin2019recurrent,
                    title={Recurrent attentive neural process for sequential data},
                    author={Qin, Shenghao and Zhu, Jiacheng and Qin, Jimmy and Wang, Wenshuo and Zhao, Ding},
                    journal={arXiv preprint arXiv:1910.09323},
                    year={2019}
                  }
                

 
                @inproceedings{zhu2018tempt,
                    title={A tempt to unify heterogeneous driving databases using traffic primitives},
                    author={Zhu, Jiacheng and Wang, Wenshuo and Zhao, Ding},
                    booktitle={2018 21st International Conference on Intelligent Transportation Systems (ITSC)},
                    pages={2052--2057},
                    year={2018},
                    organization={IEEE}
                  }