Programmes

  1. Multimodal reasoning post-training

    Can reinforcement learning teach multimodal models to reason about cause and effect, and how do we know the gain is real?

    Current research

  2. Causal faithfulness

    Does the reasoning a model states actually cause its answer? We test it by intervention.

    Current research

  3. Factual representations

    What do models represent internally, and which of it does their reasoning actually use?

    Current research