Jiacheng Zhu

Postdoc Associate

Computer Science and Artificial Intelligence Laboratory (CSAIL)

Massachusetts Institute of Technology

zjc [AT] mit.edu

[CV]

About

I am currently a postdoc at MIT CSAIL, working with Justin Solomon and Marzyeh Ghassemi. I obtaiend my Ph.D. from Carnegie Mellon Univeristy, as well as an M.S. in Machine Learning. I am fourtunate to have Prof. Long Nguyen to be my academia advisor, and I work closely with Prof. Bo Li. My research was awarded the Qualcomm Innovation Fellowship (QIF 2022). I have worked as a research intern at Apple AI/ML and AT&T Labs. Previously, I received my bachelor's in Computational Mechanics and a minor in Data Science from Fudan University.

My research focuses on developing generalizable and trustworthy foundation models and machine learning methods . Specifically, I work on fine-tuning, LLM efficiency and compression, mixture-of-experts (MoE), mechanisms of foundation models, and their applications in healthcare and robotics. I extract insights from Bayesian statistics, probabilistic modeling, and particularly optimal transport, to investigate the underlying geometric structures within both data and model parameters.

News

Publications

Most recent publications on Google Scholar.

Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead

Rickard Brüel Gabrielsson, Jiacheng Zhu, Onkar Bhardwaj, Leshem Choshen, Kristjan Greenewald, Mikhail Yurochkin, Justin Solomon

ICML ES-FoMo workshop,2024

MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos

Jielin Qiu, Jiacheng Zhu, William Han, Aditesh Kumar, Karthik Mittal, Claire Jin, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Ding Zhao, Bo Li, Lijuan Wang

CVPR 2024: Highlight

Asymmetry in Low-Rank Adapters of Foundation Models

Jiacheng Zhu, Kristjan Greenewald, Kimia Nadjahi, Haitz Sáez de Ocáriz Borde, Rickard Brüel Gabrielsson, Leshem Choshen, Marzyeh Ghassemi, Mikhail Yurochkin, Justin Solomon

ICML 2024: International Conference on Machine Learning. 2024

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

Jiacheng Zhu*, Aritra Guha*, Dat Do*, Mengdi Xu, XuanLong Nguyen, Ding Zhao.

Under review by JMLR: Journal of Machine Learning Research

Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics

Jiacheng Zhu, Jielin Qiu, Aritra Guha, Zhuolin Yang, XuanLong Nguyen, Bo Li, Ding Zhao

ICML 2023: International Conference on Machine Learning. 2023

Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation

Peide Huang, Mengdi Xu, Jiacheng Zhu, Laixi Shi, Ding Zhao

NeurIPS 2022: Conference on Neural Information Processing Systems, 2022

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

Jiacheng Zhu*, Jielin Qiu*, Zhuolin Yang, Douglas Weber, Michael Rosenberg, Emerson Liu, Bo Li, Ding Zhao.

MLHC 2022: Machine Learnign for Healthcare, 2022

Earlier version at ICLR 2022 Workshop on Socially Responsible Machine Learning .

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

Jiacheng Zhu, Gregory Darnell, Agni Kumar, Ding Zhao, Bo Li, Xuanlong Nguyen, Shirley Ren

CHIL 2022: Conference on Health, Inference, and Learning, 2022

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

Mengdi Xu, Wenhao Ding, Jiacheng Zhu, Zuxin Liu, Baiming Chen, Ding Zhao

NeurIPS 2020: Conference on Neural Information Processing Systems, 2020

Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead

Rickard Brüel Gabrielsson, Jiacheng Zhu, Onkar Bhardwaj, Leshem Choshen, Kristjan Greenewald, Mikhail Yurochkin, Justin Solomon

ICML ES-FoMo workshop,2024

MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos

Jielin Qiu, Jiacheng Zhu, William Han, Aditesh Kumar, Karthik Mittal, Claire Jin, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Ding Zhao, Bo Li, Lijuan Wang

CVPR 2024: Highlight

Asymmetry in Low-Rank Adapters of Foundation Models

Jiacheng Zhu, Kristjan Greenewald, Kimia Nadjahi, Haitz Sáez de Ocáriz Borde, Rickard Brüel Gabrielsson, Leshem Choshen, Marzyeh Ghassemi, Mikhail Yurochkin, Justin Solomon

ICML 2024: International Conference on Machine Learning. 2024

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

Jiacheng Zhu*, Aritra Guha*, Dat Do*, Mengdi Xu, XuanLong Nguyen, Ding Zhao.

Under review by JMLR: Journal of Machine Learning Research

Automated Cardiovascular Record Retrieval by Multimodal Learning between Electrocardiogram and Clinical Report

Jielin Qiu*, Jiacheng Zhu*, Shiqi Liu, William Han, Jingqi Zhang, Chaojing Duan, Michael A. Rosenberg, Emerson Liu, Douglas Weber, Ding Zhao.

ML4H 2023: Machine Learnign for Health, 2023

Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning

Yihang Yao, Zuxin Liu, Zhepeng Cen, Jiacheng Zhu, Wenhao Yu, Tingnan Zhang, Ding Zhao

NeurIPS 2023: Conference on Neural Information Processing Systems, 2023

Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics

Jiacheng Zhu, Jielin Qiu, Aritra Guha, Zhuolin Yang, XuanLong Nguyen, Bo Li, Ding Zhao

ICML 2023: International Conference on Machine Learning. 2023

Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation

Peide Huang, Mengdi Xu, Jiacheng Zhu, Laixi Shi, Ding Zhao

NeurIPS 2022: Conference on Neural Information Processing Systems, 2022

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

Jiacheng Zhu*, Jielin Qiu*, Zhuolin Yang, Douglas Weber, Michael Rosenberg, Emerson Liu, Bo Li, Ding Zhao.

MLHC 2022: Machine Learnign for Healthcare, 2022

Earlier version at ICLR 2022 Workshop on Socially Responsible Machine Learning .

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

Jiacheng Zhu, Gregory Darnell, Agni Kumar, Ding Zhao, Bo Li, Xuanlong Nguyen, Shirley Ren

CHIL 2022: Conference on Health, Inference, and Learning, 2022

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

Mengdi Xu, Wenhao Ding, Jiacheng Zhu, Zuxin Liu, Baiming Chen, Ding Zhao

NeurIPS 2020: Conference on Neural Information Processing Systems, 2020

Automated Cardiovascular Record Retrieval by Multimodal Learning between Electrocardiogram and Clinical Report

Jielin Qiu*, Jiacheng Zhu*, Shiqi Liu, William Han, Jingqi Zhang, Chaojing Duan, Michael A. Rosenberg, Emerson Liu, Douglas Weber, Ding Zhao.

ML4H 2023: Machine Learnign for Health, 2023

Cardiac Disease Diagnosis on Imbalanced Electrocardiography Data Through Optimal Transport Augmentation

Jielin Qiu*, Jiacheng Zhu*, Mengdi Xu, Peide Huang, Michael Rosenberg, Douglas Weber, Emerson Liu, Ding Zhao

ICASSP 2023: IEEE International Conference on Acoustics, Speech and Signal Processing 2023

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

Jielin Qiu*, William Han*, Jiacheng Zhu, Mengdi Xu, Michael Rosenberg, Emerson Liu, Douglas Weber, Ding Zhao

EACL 2023 Findings: Findings of the Association for Computational Linguistics, 2023

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

Jiacheng Zhu*, Jielin Qiu*, Zhuolin Yang, Douglas Weber, Michael Rosenberg, Emerson Liu, Bo Li, Ding Zhao.

MLHC 2022: Machine Learnign for Healthcare, 2022

Earlier version at ICLR 2022 Workshop on Socially Responsible Machine Learning .

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

Jiacheng Zhu, Gregory Darnell, Agni Kumar, Ding Zhao, Bo Li, Xuanlong Nguyen, Shirley Ren

CHIL 2022: Conference on Health, Inference, and Learning, 2022

Re-vibe: vibration-based indoor person re-identification through cross-structure optimal transport

Yiwen Dong, Jiacheng Zhu, Hae Young Noh

BuildSys 2022: The 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, 2022

Goats: Goal sampling adaptation for scooping with curriculum reinforcement learning

Yaru Niu, Shiyu Jin, Zeqing Zhang, Jiacheng Zhu, Ding Zhao, Liangjun Zhang

IROS 2023: International Conference on Intelligent Robots and Systems , 2023

Robustness Certification of Visual Perception Models via Camera Motion Smoothing

Hanjiang Hu, Zuxin Liu, Linyi Li, Jiacheng Zhu, Ding Zhao

CoRL 2022: Conference on Robot Learning, 2022

Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling

Mengdi Xu, Peide Huang, Fengpei Li, Jiacheng Zhu, Xuewei Qi, Kentaro Oguchi, Zhiyuan Huang, Henry Lam, Ding Zhao

IROS 2022, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022

Spatiotemporal learning of multivehicle interaction patterns in lane-change scenarios

Chengyuan Zhang, Jiacheng Zhu, Wenshuo Wang, Junqiang Xi

IEEE Transactions on Intelligent Transportation Systems, 2021

Context-aware safe reinforcement learning for non-stationary environments

Baiming Chen, Zuxin Liu, Jiacheng Zhu, Mengdi Xu, Wenhao Ding, Liang Li, Ding Zhao

ICRA 2021, IEEE International Conference on Robotics and Automation, 2021

A tempt to unify heterogeneous driving databases using traffic primitives

Jiacheng Zhu, Wenshuo Wang, Ding Zhao

ITSC 2018, 21st International Conference on Intelligent Transportation Systems, 2018

Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead

Rickard Brüel Gabrielsson, Jiacheng Zhu, Onkar Bhardwaj, Leshem Choshen, Kristjan Greenewald, Mikhail Yurochkin, Justin Solomon

ICML ES-FoMo workshop,2024

MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos

Jielin Qiu, Jiacheng Zhu, William Han, Aditesh Kumar, Karthik Mittal, Claire Jin, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Ding Zhao, Bo Li, Lijuan Wang

CVPR 2024: Highlight

Asymmetry in Low-Rank Adapters of Foundation Models

Jiacheng Zhu, Kristjan Greenewald, Kimia Nadjahi, Haitz Sáez de Ocáriz Borde, Rickard Brüel Gabrielsson, Leshem Choshen, Marzyeh Ghassemi, Mikhail Yurochkin, Justin Solomon

ICML 2024: International Conference on Machine Learning. 2024

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

Jiacheng Zhu*, Aritra Guha*, Dat Do*, Mengdi Xu, XuanLong Nguyen, Ding Zhao.

Under review by JMLR: Journal of Machine Learning Research, 2023

Automated Cardiovascular Record Retrieval by Multimodal Learning between Electrocardiogram and Clinical Report

Jielin Qiu*, Jiacheng Zhu*, Shiqi Liu, William Han, Jingqi Zhang, Chaojing Duan, Michael A. Rosenberg, Emerson Liu, Douglas Weber, Ding Zhao.

ML4H 2023: Machine Learnign for Health, 2023

Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning

Yihang Yao, Zuxin Liu, Zhepeng Cen, Jiacheng Zhu, Wenhao Yu, Tingnan Zhang, Ding Zhao

NeurIPS 2023: Conference on Neural Information Processing Systems, 2023

Goats: Goal sampling adaptation for scooping with curriculum reinforcement learning

Yaru Niu, Shiyu Jin, Zeqing Zhang, Jiacheng Zhu, Ding Zhao, Liangjun Zhang

IROS 2023: International Conference on Intelligent Robots and Systems , 2023

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

Jielin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Bo Li, Ding Zhao, Hailin Jin

ACL 2023: Findings of the Association for Computational Linguistics

Cardiac Disease Diagnosis on Imbalanced Electrocardiography Data Through Optimal Transport Augmentation

Jielin Qiu*, Jiacheng Zhu*, Mengdi Xu, Peide Huang, Michael Rosenberg, Douglas Weber, Emerson Liu, Ding Zhao

ICASSP 2023: IEEE International Conference on Acoustics, Speech and Signal Processing 2023

Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics

Jiacheng Zhu, Jielin Qiu, Aritra Guha, Zhuolin Yang, XuanLong Nguyen, Bo Li, Ding Zhao

ICML 2023: International Conference on Machine Learning. 2023

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

Jielin Qiu*, William Han*, Jiacheng Zhu, Mengdi Xu, Michael Rosenberg, Emerson Liu, Douglas Weber, Ding Zhao

EACL 2023 Findings: Findings of the Association for Computational Linguistics, 2023

Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation

Peide Huang, Mengdi Xu, Jiacheng Zhu, Laixi Shi, Ding Zhao

NeurIPS 2022: Conference on Neural Information Processing Systems, 2022

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

Jiacheng Zhu*, Jielin Qiu*, Zhuolin Yang, Douglas Weber, Michael Rosenberg, Emerson Liu, Bo Li, Ding Zhao.

MLHC 2022: Machine Learnign for Healthcare, 2022

Earlier version at ICLR 2022 Workshop on Socially Responsible Machine Learning .

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

Jiacheng Zhu, Gregory Darnell, Agni Kumar, Ding Zhao, Bo Li, Xuanlong Nguyen, Shirley Ren

CHIL 2022: Conference on Health, Inference, and Learning, 2022

Robustness Certification of Visual Perception Models via Camera Motion Smoothing

Hanjiang Hu, Zuxin Liu, Linyi Li, Jiacheng Zhu, Ding Zhao

CoRL 2022: Conference on Robot Learning, 2022

Re-vibe: vibration-based indoor person re-identification through cross-structure optimal transport

Yiwen Dong, Jiacheng Zhu, Hae Young Noh

BuildSys 2022: The 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, 2022

Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling

Mengdi Xu, Peide Huang, Fengpei Li, Jiacheng Zhu, Xuewei Qi, Kentaro Oguchi, Zhiyuan Huang, Henry Lam, Ding Zhao

IROS 2022, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022

Spatiotemporal learning of multivehicle interaction patterns in lane-change scenarios

Chengyuan Zhang, Jiacheng Zhu, Wenshuo Wang, Junqiang Xi

IEEE Transactions on Intelligent Transportation Systems, 2021

Context-aware safe reinforcement learning for non-stationary environments

Baiming Chen, Zuxin Liu, Jiacheng Zhu, Mengdi Xu, Wenhao Ding, Liang Li, Ding Zhao

ICRA 2021, IEEE International Conference on Robotics and Automation, 2021

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

Mengdi Xu, Wenhao Ding, Jiacheng Zhu, Zuxin Liu, Baiming Chen, Ding Zhao

NeurIPS 2020: Conference on Neural Information Processing Systems, 2020

Recurrent Attentive Neural Process for Sequential Data

Shenghao Qin*, Jiacheng Zhu*, Jimmy Qin, Wenshuo Wang, Ding Zhao

NeurIPS 2019, Workshop on Learning with Rich Experience, 2019

A tempt to unify heterogeneous driving databases using traffic primitives

Jiacheng Zhu, Wenshuo Wang, Ding Zhao

ITSC 2018, 21st International Conference on Intelligent Transportation Systems, 2018

Professional Service

Organizer
  • NeurIPS 2024 LLM Merging Competition
  • Conference on Health, Inference, and Learning (CHIL) 2024
  • Round Table Chiar of Machine Learning for Health 2023
  • Reviewer mentorship program of Machine Learning for Health 2023
  • ICRA 2023 Season Depth Challenge
Conference Reviewer

NeurIPS / ICLR / ICML / AISTATS(Top reviewer 2023) / AAAI / CHIL / MLHC / ML4H

Journal Reviewer

TPAMI / TMLR / RA-L / IEEE T-ITS / IEEE T-IV

Acknowledgement

This website was built with jekyll based on a template by Martin Saveski.