Chen Bo Calvin Zhang

ML Research Ops Lead @ Scale AI | Previously @ CHAI, MIT, ETH Zurich, and University of Manchester

profile_photo.jpg

I am currently the ML Research Ops Lead at Scale AI, where I work on evaluations, benchmarks and leaderboards.

Before joining Scale AI, I was a research intern at CHAI, where I worked with Micah Carroll on red teaming large language models. I also spent time as a visiting scholar at MIT, where I focused on online learning and reward design for reinforcement learning. During that time, I was fortunate to collaborate with Zhang-Wei Hong, Aldo Pacchiano, and Pulkit Agrawal.

I hold an MSc in Data Science from ETH Zurich, where I worked with Giorgia Ramponi on preference-based reinforcement learning.

Earlier, I completed my BSc (Hons) in Computer Science and Mathematics at the University of Manchester, where I researched adversarial attacks in deep reinforcement learning under the supervision of Tingting Mu.

I am interested in sequential decision making and AI safety and alignment.

Google Scholar  /  Twitter  /  GitHub  /  LinkedIn

News

Jun 19, 2025 Excited to share our new paper SHADE-Arena, in collaboration with Anthropic!
Jan 27, 2025 I am excited to join Scale AI as a ML Research Ops Lead!

Latest Posts

Selected Publications

  1. ICLR
    ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization
    Chen Bo Calvin Zhang, Zhang-Wei Hong, Aldo Pacchiano, and Pulkit Agrawal
    In The Thirteenth International Conference on Learning Representations, 2025
  2. arXiv
    Humanity’s Last Exam
    Long Phan, Alice Gatti, Ziwen Han, Nathaniel Li, Josephina Hu, Hugh Zhang, Chen Bo Calvin Zhang, Mohamed Shaaban, John Ling, and 2 more authors
    arXiv preprint arXiv:2501.14249, 2025
  3. Preprint
    SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
    Jonathan Kutasov, Yuqi Sun, Paul Colognese, Teun Weij, Linda Petrini, Chen Bo Calvin Zhang, John Hughes, Xiang Deng, Henry Sleight, and 3 more authors
    2025
  4. ICML
    HIP-RL: Hallucinated Inputs for Preference-based Reinforcement Learning in Continuous Domains
    Chen Bo Calvin Zhang, and Giorgia Ramponi
    In ICML 2023 Workshop: The Many Facets of Preference-Based Learning, 2023