Yadia / Research
Research
We post-train multimodal models with reinforcement learning, test whether their stated reasoning is faithful, and measure what they represent inside.
Programmes
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
Causal faithfulness
Does the reasoning a model states actually cause its answer? We test it by intervention.
Current research
Factual representations
What do models represent internally, and which of it does their reasoning actually use?
Current research