Haozhe Zhang

Palo Alto, CA

USA

Hey, welcome to my page! 👋

I’m a modeling engineer at Tesla, working at the intersection of physics-based modeling and machine learning for next-generation battery cells — theoretical and computational modeling, reinforcement learning for automation, and data-driven optimization at scale-up.

Beyond physics, I work on large language models and agentic systems, with hands-on experience building LLM-powered voice agents (krono) and RL-based infrastructure for decision-making and automation.

Before Tesla, I earned my PhD in mechanical engineering from the University of Virginia and a BS from the University of Science and Technology of China.

In my spare time, I enjoy traveling and playing Leagues.

news

May 11, 2026	Our new paper “BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD” is now on arXiv. Read it here.
Nov 30, 2025	Our voice agent for stock trading and news gathering is launched and open for registration. Try it here.
Nov 10, 2025	Our voice agent for stock trading and news gathering is comming soon, here is the official webpage: krono.
Aug 15, 2025	Our paper “A buckling mechanics model for pattern transformation of lattice superstructures assembled by soft-hard materials integrated units” has been published in ACS Applied Polymer Materials.
Apr 23, 2025	Our paper “Degradation of Hydrogen Bonds Enormously Enhances Convective Heat Transfer in Nanofluidics” has been published in Nano Letters. Read it here.
Sep 20, 2024	Our paper “Extremely durable electrical impedance tomography–based soft and ultrathin wearable e-skin for three-dimensional tactile interfaces” has been published in Science Advances. Read it here.
Feb 10, 2023	Our paper “Mechanical Janus Structures by Soft–Hard Material Integration” has been published featured as inside cover. Here is the link.
Nov 30, 2022	Our paper “Mechanical Janus Structures by Soft‐Hard Material Integration” has been published on Advanced Materials. Here is the link.
Nov 10, 2022	Our paper “Soft-hard material integration enabled programmable robotic locomotion” has been published on Applied Physics Letter. Here is the link.
Aug 13, 2022	Completed an 3-month Internship at Western Digital. I thoroughly enjoyed working with the team on packaging team.

featured

BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD

Haozhe Zhang, Kaichen Liu, Miaomiao Chen, Lei Li, Shaojie Yang, Cheng Peng, and Hanjie Chen

2026

Abs HTML

We present BenchCAD, a comprehensive industry-standard benchmark for evaluating programmatic CAD code generation. The benchmark includes over 17,000 execution-verified CadQuery programs spanning 106 industrial part families (e.g., gears, springs, drills) and assesses models across visual question answering, code analysis, image-to-code conversion, and code editing. Our results show that current models often recover coarse outer geometry but fail to produce faithful parametric CAD programs, with common failure modes including missing structural details and oversimplified operations; generalization to unseen part families remains limited even after fine-tuning.
Sci. Adv.

Extremely durable electrical impedance tomography–based soft and ultrathin wearable e-skin for three-dimensional tactile interfaces

Kyungbin Kim, Jung-Hoon Hong, Kyungtaek Bae, Kunhee Lee, Dong Jun Lee, Junseong Park, Haozhe Zhang, Mingyu Sang, Ji-Eun Ju, and others

2024

Abs HTML

We introduce a thin and soft electrical impedance tomography (EIT) based e-skin for tactile interfaces. The conductive and stretchable sensing domain uses a micropatterned multi-walled carbon nanotube/elastomer composite. The EIT-based tactile interface discerns external pressures to a sub-millimeter degree and vertical deformations of a few hundred micrometers, sustaining stable functions under damage or environmental changes. We demonstrate real-time human–machine interface applications including handwriting recognition and drone control.
Mechanical Janus Structures by Soft‐Hard Material Integration

Haozhe Zhang, Weizhu Yang, Qingchang Liu, Yuan Gao, Zhufeng Yue, and Baoxing Xu

2022

Abs HTML

Engineering Janus structures that possess anisotropic features in functions have attracted growing attention for a wide range of applications in sensors, catalysis, and biomedicine, and are yet usually designed at the nanoscale with distinct physical or chemical functionalities in their opposite sides. Inspired by the seamless integration of soft and hard materials in biological structures, here we present a mechanical Janus structure composed of soft and hard materials with a dramatic difference of mechanical properties at additively manufacturable macroscale. We establish, in the combination of extensive experimental, theoretical, and computational studies, the design principle of soft-hard materials integrated mechanical Janus structures and address their unique rotation mechanism. We further show the systematic studies of assembling the Janus structure units into superstructures with well-ordered organizations by programing their local rotations, providing a direct route of designing superstructures by leveraging mechanical Janus structures with unique soft-hard material integration. Applications are conducted to demonstrate the features and functionalities of assembled superstructures with local ordered organizations in regulating and filtering acoustic wave propagations, thereby providing exemplification applications of mechanical Janus design in functional structures and devices.