Andrei Barbu

Researcher@MIT·美国·OpenReview

研究方向

robotics · ai · language acquisition · grounded language acquisition · language and vision · neuroscience of language · neuroscience of vision · object recognition · dataset design · social intearctions · activity recognition

7.5

Population Transformer: Learning Population-level Representations of Neural Activity

ICLR 2025Oral

通讯

6.0

Training the Untrainable: Introducing Inductive Bias via Representational Alignment

ICLR 2025Rejected

通讯

4.0

Using Multimodal Deep Neural Networks to Disentangle Language from Visual Aesthetic Experience

合作者 (20)

Andrei Barbu

Population Transformer: Learning Population-level Representations of Neural Activity

Training the Untrainable: Introducing Inductive Bias via Representational Alignment

Using Multimodal Deep Neural Networks to Disentangle Language from Visual Aesthetic Experience

BrainBits: How Much of the Brain are Generative Reconstruction Methods Using?

ObjectNet Captions: Models are not superhuman captioners

Revealing Vision-Language Integration in the Brain with Multimodal Networks