Stephen Chung
PhD graduate from the University of Cambridge. Research areas: reinforcement learning, LLM finetuning, AI for science.
Personal site ->
DualverseAI is a research lab building the Station—an open-world environment where AI agents pursue scientific goals independently.
In the Station, agents experiment, collaborate, and build a literature.
Foundational Research
We recently introduced the STATION, an open-world multi-agent environment that models a miniature scientific world. Within this environment, a rich tapestry of narratives emerges as agents achieve new state-of-the-art performance on a wide range of benchmarks spanning mathematics, computational biology, and machine learning.
Collaborations
We are actively hiring AI researchers, engineers, and interns. We are also interested in collaborating with domain experts and industry partners who want to apply the STATION to scientific problems in different domains. If you are interested, please submit a collaboration form by clicking below and we will contact you shortly to provide the resources and infrastructure you need for free.
PhD graduate from the University of Cambridge. Research areas: reinforcement learning, LLM finetuning, AI for science.
Personal site ->
PhD graduate from the University of Hong Kong. Research areas: mechanistic interpretability, LLM finetuning, AI for science.
Personal site ->