7 accepted papers
Memory formation is fundamental to intelligence, yet whether deep neural networks preserve identifiable memory traces—analogous to biological memory units—remains an open question. This work introduces a geometric framework to identify such "AI engrams," by formalizing the neuroscientific criteria o…
The reversal curse---a language model's (LM) inability to infer an unseen fact ``B is A'' from a learned factA is B''---is widely considered a fundamental limitation. We show that this is not an inherent failure but an artifact of how models encode knowledge. By training LMs from scratch on a synthe…
Humans display significant uncertainty when confronted with moral dilemmas, yet the extent of such uncertainty in machines and AI agents remains underexplored. Recent studies have confirmed the overly confident tendencies of machine-generated responses, particularly in large language models (LLMs).
Large language models trained on web-scale data can memorize private or sensitive knowledge, raising significant privacy risks. Although some unlearning methods mitigate these risks, they remain vulnerable to "relearning" during subsequent training, allowing a substantial portion of forgotten knowle…
Geospatial understanding is a critical yet underexplored dimension in the development of machine learning systems for tasks such as image geolocation and spatial reasoning. In this work, we analyze the geospatial representations acquired by three model families: vision-only architectures (e.g., ViT)…
Convolutional Neural Networks (CNNs) have profoundly influenced the field of computer vision, drawing significant inspiration from the visual processing mechanisms inherent in the brain. Despite sharing fundamental structural and representational similarities with the biological visual system, diffe…
The hippocampus plays a critical role in learning, memory, and spatial representation, processes that depend on the NMDA receptor (NMDAR). Inspired by recent findings that compare deep learning models to the hippocampus, we propose a new nonlinear activation function that mimics NMDAR dynamics. NMDA…