Hao Wang

I am a Ph.D. student at Texas A&M University advised by Prof. Zhiwen Fan, and a Senior Research Engineer at Google DeepMind working on Gemini post-training and safety alignment.

Previously, I received my M.Sc. from Carnegie Mellon University and my B.Sc. from the University of Edinburgh, where I was advised by Prof. Hakan Bilen.

  • Agentic RL & post-training
  • Continual learning
  • AI alignment
  • Robot learning
  • World models
Portrait of Hao Wang

News

Publications

* equal contribution

2026

CoRL 2026 Workshop · Scaling H2R2610.10288

TouchScale: 500 Hours of Human Vision and Touch for Visual–Tactile Learning

Dayou Li*, Hao Wang*, Qianqian Yang*, Zihao Zhu*, Haoquan Fang, Ziyao Zeng, Yan Han, , Zhiwen Fan

A 500-hour dataset pairing egocentric video with full-hand tactile signals; scaling it raises robot task success from 22.5% to 57.5% and improves zero-shot touch prediction on unseen sensors.

CoRL 2026 Workshop · Grounded 4D World Models🏆 Best Paper Award

OpenLongTail: Generative Scaling of Long-Tail Driving Data

Lulin Liu*, Nuo Chen*, Yan Wang, Bangya Liu, Wenyan Cong, Hezhen Hu, Boris Ivanovic, Hao Wang, , Zhiwen Fan

An open-source generative data engine that turns long-tail driving videos, even single dash-cam clips, into pose-grounded multi-view data for VLA policy learning.

CoRL 2026 Workshop · LBR

TouchTwin: Scaling Human Touch Data via Real-to-Sim-to-Real

Huiwen Han*, Nuo Chen*, Ziyao Zeng*, Dayou Li, Hao Wang, Amir Hossein Rahmati, Xiaoning Qian, Bangya Liu, Zhiwen Fan

Rebuilds TouchScale glove recordings in simulation with touch-driven contact forces; policies trained on these replays grip at 0.99× the recorded force, versus 0.31× for pose imitation.

arXiv 20262610.19005

CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat

Bangya Liu, Jianhong Tu, Yueyang Pan, Hanhong Zhao, , Hao Wang, Zhiwen Fan, Tianneng Shi, Zhun Wang, Wenbo Guo, Chenguang Wang, Dawn Song

A live attack-and-defense CTF benchmark: two agents exploit each other's service while patching their own over multiple rounds, with a latent-ability model placing offense, defense and difficulty on one scale.

2025
2024
2023

Education

  • Texas A&M UniversityPh.D. in Computer Engineering2026 – now
  • Carnegie Mellon UniversityM.Sc. in Computer Science2021 – 2022
  • University of EdinburghB.Sc. Artificial Intelligence and Computer ScienceFirst-Class Honours2017 – 2020

Experience

  • Google DeepMindSenior Research EngineerGemini Post-Training & Safety Alignment2022 – now
  • ByteDanceMachine Learning Engineer Intern2020.12 – 2021.07
  • University of EdinburghResearch AssistantVisual Computing Group (VICO)2019.06 – 2020.05

Awards

  • University of Edinburgh Class Medal (highest GPA in the undergraduate cohort)
  • Carnegie Mellon University Director's Scholarship
  • Spiritus Prize for Health and Wellbeing

Service & Teaching

  • Reviewer: ICLR, ACL, COLM, BMVC
  • TA, University of Edinburgh: Algorithms, Data Structures, Machine Learning, Software Engineering
  • TA, Carnegie Mellon University: 17-637 Web Application Development