Publications

 
            @misc{liang2025modomodo,
              title={MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning},
              author={Yiqing Liang and Jielin Qiu and Wenhao Ding and Zuxin Liu and James Tompkin and Mengdi Xu and Mengzhou Xia and Zhengzhong Tu and Laixi Shi and Jiacheng Zhu},
              year={2025},
              eprint={2505.24871},
              archivePrefix={arXiv},
              primaryClass={cs.LG}
            }
          

 
            @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={2025},
              eprint={2407.00066},
              archivePrefix={arXiv},
              primaryClass={cs.DC}
            }
          

 
            @inproceedings{tam2024llm,
              title={LLM Merging: Building LLMs Efficiently through Merging},
              author={Derek Tam and Margaret Li and Prateek Yadav and Rickard Brøel Gabrielsson and Jiacheng Zhu and Kristjan Greenewald and Mikhail Yurochkin and Mohit Bansal and Colin Raffel and Leshem Choshen},
              booktitle={Advances in Neural Information Processing Systems},
              year={2024}
            }
          

 
            @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={2025},
            }
          

 
            @article{zhu2024functional,
                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},
                journal={Journal of Machine Learning Research},
                year={2024}
            }
          

 
            @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}
              }