Andrei Barbu

Researcher@Massachusetts Institute of Technology·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

5.5

Neuroprobe: Evaluating Intracranial Brain Responses to Naturalistic Stimuli

ICLR 2026Rejected

4.0

Network of Theseus (like the ship)

ICLR 2026Rejected

3.0

SecureLLM: Using Inference-time Compositionality to Build Secure Language Models for Private, Sensitive, and Secret Data

ICLR 2026Rejected

2.5

Training the Untrainable: Introducing Inductive Bias via Representational Alignment

合作者 (20)

Christian Michael Arnold

Andrei Barbu

Neuroprobe: Evaluating Intracranial Brain Responses to Naturalistic Stimuli

Network of Theseus (like the ship)

SecureLLM: Using Inference-time Compositionality to Build Secure Language Models for Private, Sensitive, and Secret Data

Look but Don’t Touch: Gradient Informed Selection Training

How Predictable is AI Progress?

MapQA: A Map-Question-Answering Benchmark for Visual Language Model Reasoning

Training the Untrainable: Introducing Inductive Bias via Representational Alignment