Haoran Zhang

Hi! I am a PhD student in WNCG Group, ECE UT-Austin, advised by Prof. Haris Vikalo. I previously completed my MS in ECE at CMU. During my time at CMU, I worked with Prof. Carlee Joe-Wong on federated learning. I am also working with Prof. Marie Siew and Prof. Rachid El-Azouzi. I got my bachelor's degree from Huazhong University of Science and Technology. During the undergrad study, I worked on AI for healthcare with Prof. Hao Chen at HKUST.

I am open to summer 2027 internship opportunities. My ongoing research focuses on resource optimization for collaborative LLM agent systems under realistic budget constraints. Please feel free to reach out if there may be a good match.

Email  /  Resume [Template] /  Scholar  /  Github /  LinkedIn

profile photo

Research

My ongoing research includes:
(1) Resource (budget, latency, etc) optimization for collaborative LLM agent systems,
(2) Parameter-effcient fine-tuning for LLMs in a distributed manner,
(3) Hierarchical inference system with multiple tasks, models, layers, and nodes.
I am open to collaborations on related topics, please feel free to reach out.

My research at UT-Austin

FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA
Haoran Zhang, Dongjun Kim, Seohyeon Cha, Haris Vikalo
ICML, 2026
Online Learning for Multi-Layer Hierarchical Inference under Partial and Policy-Dependent Feedback
Haoran Zhang, Seohyeon Cha, Hasan Burhan Beytur, Kevin S Chan, Gustavo de Veciana, Haris Vikalo
Regularized Calibration with Successive Rounding for Post-Training Quantization
Seohyeon Cha, Huancheng Chen, Dongjun Kim, Haoran Zhang, Kevin S Chan, Gustavo de Veciana, Haris Vikalo

My research at CMU

FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching
Haoran Zhang, Cainã Figueiredo Pereira, Marie Siew, Xutong Liu, Carlee Joe-Wong, Rachid El-Azouzi
UAI, 2026
Optimally Leveraging Stale Updates in Federated Learning
Haoran Zhang
SIGMETRICS Student Research Competition, 2025
Fair Concurrent Training of Multiple Models in Federated Learning
Marie Siew, Haoran Zhang, Jong-Ik Park, Yuezhou Liu, Yichen Ruan, Lili Su, Stratis Ioannidis, Edmund Yeh, Carlee Joe-Wong
IEEE Transactions on Networking, 2025
Supplementary material
Poster: Optimal Variance-Reduced Client Sampling for Multiple Models Federated Learning
Haoran Zhang, Zekai Li, Zejun Gong, Marie Siew, Carlee Joe-Wong, Rachid El-Azouzi
ICDCS, 2024 [Best Poster Award] [Poster]
Supplementary material
Group-based Client Sampling in Multi-Model Federated Learning
Zejun Gong*, Haoran Zhang*, Marie Siew, Carlee Joe-Wong, Rachid El-Azouzi
VTC, Spring 2025. *Equal contribution
Towards Optimal Heterogeneous Client Sampling in Multi-Model Federated Learning
Haoran Zhang, Zejun Gong, Zekai Li, Marie Siew, Carlee Joe-Wong, Rachid El-Azouzi

My research at HKUST: Medical AI

Efficient 3D Transformer with cluster-based Domain-Adversarial Learning for 3D Medical Image Segmentation
Haoran Zhang, Hao Chen
ISBI, 2023

Some Presentations

Distributed Intelligence for LLMs
Guest lecture for 50.041 Distributed Systems and Computing (SUTD), Apr 13, 2026
From Centralized Learning to Federated Learning
CMU 18786 Recitation, Apr 11, 2025
Trade-off between client sampling and training stability
CMU LIONS group seminar, Sep 27, 2024
Topics on Multi-Model Federated Learning (about our ICDCS poster)
CMU LIONS group seminar, May 17, 2024

Teaching and Mentoring

Teaching Assistant
18786 Introduction to Deep Learning (Spring 2025)
ECE Peer Mentor
Mentees (Spring 2025): Mary Tonwe, Fanyun Xu, Han Zhou

Education

About Me

I was born in Xinxiang, China. My family name is 张 (Zhang), which is one of the most common family names in China. And my given name is 皓然 (Haoran), 皓(Hao) means "the color of the moon", 然(Ran) doesn't have a specific meaning, maybe it means "yeah, uh-huh". As the first in my family to attend college, I am deeply grateful for the support from my parents, mentors, and friends.


Template stolen from Jon Barron.
Last updated: