About me

I am Dinghuai Zhang (张鼎怀), working on reasoning & coding RL at xAI.

Before that, I was a senior researcher at Microsoft Research New England. I obtained my PhD at Mila in Prof. Bengio’s group as well as Aaron’s Army (aka A.A.). During my PhD, I’ve interned at Apple MLR and FAIR labs. Previously, I was an undergraduate in School of Mathematical Sciences at Peking University, working with Prof. Zhanxing Zhu and Prof. Bin Dong.

Research interests (back when at academia)

I aim to tackle multidisciplinary problems with generative models and probabilistic methods.

• Stability and efficiency of large language model RL
• Exploration with structure in RL, black-box optimization, search
• Multimodal generative modeling

I’ve also conducted probabilistic inference (sampling, scientific discovery) and AI safety research (distribution shift, causal representation learning) before.

Activities

Organizer

• MSR New England Generative Modeling & Sampling Seminar (link).
• Safe Generative AI Workshop at NeurIPS 2024).
• Structured Probabilistic Inference & Generative Modeling (SPIGM) workshop at ICML 2023, ICML 2024, and NeurIPS 2025.
• FAI seminar (link).

Services

Area Chair of ICLR and ICML.
Reviewer of JMLR, TPAMI, ICML, NeurIPS, ICLR, AISTATS, UAI, CLeaR, EMNLP.

Miscs

• I used to be a huge fan of Daido Moriyama and Henri Cartier-Bresson (street photography pioneers).
• I paint Chinese calligraphy well since a child.
• My Erdős number is 3.