CV

Download Résumé (PDF, 1 page)

EDUCATION

• University of California, Los Angeles (Los Angeles, CA)
  • M.S. in Electrical and Computer Engineering (Expected 2027)
  • Research with Prof. Bolei Zhou (VAIL) and Prof. Kai-Wei Chang (UCLA NLP)
• University of Rochester (Rochester, NY)
  • B.S. in Computer Science and B.S. in Business, Cluster in Studio Art (May 2025)
  • GPA: 3.82/4.00
  • Honors: Highest Distinction, Cum Laude; Dean’s List (8 semesters); Schwartz Discover Grant ($5,000), 2022

RESEARCH & ENGINEERING EXPERIENCE

• Student Researcher, Vision and Autonomy Intelligence Lab (VAIL), UCLA, Prof. Bolei Zhou
  • Los Angeles, CA · Jan 2026 – Present
  • ChairNav (first author): built a data-efficient cross-embodiment training-data pipeline adapting 170 h of source teleoperation data to a Permobil M3 power wheelchair using synthetic trajectories; used imitation learning on 3.19 h of human demonstrations and human-in-the-loop post-training, achieving 84.9% autonomous driving time across 7.8 km of outdoor navigation.
  • Identified nonlinear wheelchair dynamics for physics simulation; used Isaac Sim and UrbanSim; built semi-automated RGB–LiDAR calibration, conditional auto-exposure, 3D-printed mounts, and automated robot-data reconstruction, visualization, and filtering pipelines.
  • Accelerated ChairNav model inference from 0.6 to 20 Hz through model quantization and TensorRT optimization on Jetson AGX Orin; reverse-engineered the R-net CAN bus and implemented feedforward and residual compensation. Broader engineering included GPS/IMU/odometry localization and multi-IMU / high-precision GPS data collection.
  • Cue the Flow (CoRL 2026): deployed VLM grounding and a frozen π_0.5 VLA on an AgileX PiPER arm with Jetson image processing and remote inference in a synchronous control loop; integrated the arm, power, communications, and streaming on a DEEP Robotics M20 Pro, and built semi-automated demonstration collection and cleaning.
  • Built shared perception between Meta Aria Gen 1 glasses and the M20 Pro for online mapping and target navigation; combined Aria Gen 2 streaming, gaze, head pose, image depth, and hand gestures to infer target direction, distance, and user intent.
  • Also: Booster T1 humanoid data collection; Unitree Go2 navigation host software.
• Student Researcher, UCLA NLP Group, Prof. Kai-Wei Chang
  • Los Angeles, CA · Dec 2025 – Mar 2026
  • Co-developed ToolSmith (Findings of EMNLP 2026): generated 264 verified tools from a 9,174-query pool through tool synthesis and verification, improving Qwen3-VL-8B MMSearch accuracy from 51.46% to 55.56%.
• Student Researcher, Seizure Lab, ECE Department, UCLA
  • Los Angeles, CA · Aug 2025 – Oct 2025
  • Built a clinical seizure-semiology dataset (10,000 records, 8 features) contributing to S3 (ICML 2026 Spotlight).
  • Deployed 3 VLMs with vLLM asynchronous inference and request batching, increasing throughput from 0.3 to 5 requests/s (16.7×).
• Student Researcher, Prof. Chenliang Xu’s Lab, Computer Science Department, University of Rochester
  • Rochester, NY · May 2025 – Sep 2025
  • Researched VLM-guided audio remixing (acoustic highlighting); first author of Semantic Visually-Guided Acoustic Highlighting with Large Vision-Language Models (arXiv 2026).
  • Built an asynchronous, sharded caption-embedding pipeline with chunking and prefix caching; prototyped gated-fusion and multi-head attention modules.
• Student Researcher, Prof. Jiebo Luo’s Lab, Computer Science Department, University of Rochester
  • Rochester, NY · Aug 2024 – Apr 2025
  • Reconstructed animal images from skeletons using Stable Diffusion (image-to-image); applied partial diffusion to retain segmentation and sparse-cloud encoders to inject spatial cues across large domain gaps.
  • Improved facial realism with preference optimization (DPO with LoRA fine-tuning); built preference pairs and tuned prompts and schedules on UR Linux clusters. Contributed to the Video-LMM Post-Training survey.
• Machine Learning Intern, Farsee2 Technology (Hybrid), mentored by Dr. Hailong Pan
  • Jul 2024 – Sep 2024
  • Reduced floating artifacts by approximately 40% in city-scale Gaussian Splatting with incidence-angle weighting and depth/normal supervision.
  • Built configurable multi-machine scripts that parallelized depth generation and preprocessing, integrated into the product pipeline.
• Research Assistant, Prof. Chenliang Xu’s Lab, Computer Science Department, University of Rochester
  • Rochester, NY · Apr 2024 – Aug 2024
  • Deployed, tested, and extended co-speech gesture generation models on Linux GPU servers; built, cleaned, and labeled 200 audio–gesture sequences; explored a Mamba backbone for temporal action localization; modified a ViT (Transformer++) structure. Contributed to GestureLSM (ICCV 2025).
• Student Researcher, Goergen Institute for Data Science, University of Rochester
  • Rochester, NY · Jan 2024 – Jun 2024
  • Designed two ideology-bias metrics and a blind-test harness; automated data collection and reproducible scoring for evaluating political ideology in LLMs; helped maintain a database of more than 140,000 political-ideology sentences.
  • Published in the Journal of Political Institutions and Political Economy (2025; SSRN).
• Research Assistant (Schwartz Discover Grant), University of Rochester
  • Rochester, NY · May 2022 – Dec 2022
  • Low-cost, image-based 3D/VR reconstruction of the Jamestown Settlement and Elmina Castle with Agisoft Metashape and Unity; image and point-cloud cleaning and restoration.

PUBLICATIONS

* equal contribution

• Junhua Huang*, Zhizheng Liu*, Honglin He, Xiang Zhang, Bolei Zhou. ChairNav: Cross-Embodiment Pre-training and Personalization for Long-Horizon Wheelchair Navigation. Under submission, 2026. arXiv · Project page
• Haoxuan Wang, Griffin Galimi, Junhua Huang, Selina Song, Wayne Wu, Yan Yan, Bolei Zhou. Cue the Flow: Steering Flow-Matching Policies for Open-World Delivery Manipulation. CoRL 2026. arXiv · Project page
• Rui Sun, Junhua Huang, Luca Zancato, Md Mofijul Islam, Kai-Wei Chang. ToolSmith: An Automatic Tool-Generation Framework for Multimodal Search Agents. Findings of EMNLP 2026. Project page
• Lina Zhang, Tonmoy Monsoor, et al. (incl. Junhua Huang), Rajarshi Mazumder, Vwani Roychowdhury. Seizure-Semiology-Suite (S3): A Clinically Multimodal Dataset, Benchmark, and Models for Seizure Semiology Understanding. ICML 2026 (Spotlight). arXiv
• Pinxin Liu, Luchuan Song, Junhua Huang, Haiyang Liu, Junfan Zhu, Chenliang Xu. GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling. ICCV 2025. arXiv
• Junhua Huang, Chao Huang, Chenliang Xu. Semantic Visually-Guided Acoustic Highlighting with Large Vision-Language Models. arXiv 2026. arXiv
• Pinxin Liu, Haiyang Liu, Jiahao Luo, Junhua Huang, Chunhao Zou, Luchuan Song. GestureFAR: Streaming Co-Speech Gesture Generation with Flow Autoregression. arXiv 2026. arXiv
• Yolo Y. Tang, Jing Bi, Pinxin Liu, et al. (incl. Junhua Huang), Jiebo Luo, Chenliang Xu. Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models. arXiv 2025. arXiv
• Cantay Caliskan, Junhua Huang, Yiyang Huang, Ruoxuan Lin, Wanting Shan. Using Generative AI to Calculate Party Positions: A Comparison of Human Experts and Large Language Models. Journal of Political Institutions and Political Economy, 2025. DOI · SSRN

PLATFORMS

• Robots: Permobil M3, AgileX PiPER, DEEP Robotics M20 Pro, Booster T1, Unitree Go2
• Wearable platforms: Meta Aria Gen 1 and Gen 2
• Edge computing: NVIDIA Jetson Xavier NX, NVIDIA Jetson AGX Orin

SKILLS

• Robot learning: imitation, preference, and reinforcement learning; flow matching; VLA/VLM; cross-embodiment transfer
• Robotics systems: system identification, physics-based simulation, Isaac Sim, UrbanSim, ROS/ROS2, CAN bus, TensorRT, SLAM, RGB–LiDAR calibration, 3D reconstruction
• Programming: Python, PyTorch, Linux, Java, Kotlin, C, R, SQL, JavaScript, PHP, MySQL, HTML, CSS, Git
• Software: Android Studio, IntelliJ IDEA, SolidWorks, Agisoft Metashape, Unity, Google Suite, Microsoft Office

TEACHING

• Teaching Assistant & Workshop Leader, University of Rochester
  • CSC 172 Data Structures and Algorithms (Aug 2023 – May 2024)
  • CSC 171 Introduction to Computer Science (Dec 2022 – May 2023)

PROJECTS

• Body Signals Analysis of Smoking and Drinking
  • Sep 2023 – Dec 2023
  • Preprocessed over 900k records by selecting relevant attributes through feature engineering; applied PCA to 2 principal + 2 auxiliary components, capturing the dominant variance for compact modeling.
  • Trained SVM and XGBoost for 5 categories of smoking/drinking prediction with 72/81% accuracy.
• OpenJDK 17u-dev
  • Jul 2024 – Aug 2024
  • Wrote a step-by-step guide for deploying the JDK in local Linux testing environments; contributed to testing and acceptance of pull request #2756 (8313674) on Ubuntu 22.
• IMDB Database Project
  • Aug 2023 – Dec 2023
  • Led a team of three on database compliance and security (injection-attack testing); built a login system and user-type-specific CRUD functions with JavaScript, PHP, MySQL, HTML, CSS, and Git.
• Bob’s Burgers Android App
  • Jan 2023 – May 2023
  • Solo-developed an Android app with RecyclerView, API integration, and MVVM, with robust error handling for invalid API requests.