9 citations · 22 across the 7 of their papers we have counts for
7 papers
The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
Christina Lu, Jack Gallagher, Jonathan Michala +2
Large language models can represent a variety of personas but typically default to a helpful Assistant identity cultivated during post-training. We investigate the structure of the…
Emergent Introspective Awareness in Large Language Models
Jack Lindsey
We investigate whether large language models can introspect on their internal states. It is difficult to answer this question through conversation alone, as genuine introspection c…
Action-modulated midbrain dopamine activity arises from distributed control policies
Jack Lindsey, Ashok Litwin-Kumar
Animal behavior is driven by multiple brain regions working in parallel with distinct control policies. We present a biologically plausible model of off-policy reinforcement learni…
Sequence Learning and Consolidation on Loihi using On-chip Plasticity
Jack Lindsey, James B Aimone
In this work we develop a model of predictive learning on neuromorphic hardware. Our model uses the on-chip plasticity capabilities of the Loihi chip to remember observed sequences…
Learning to Learn with Feedback and Local Plasticity
Jack Lindsey, Ashok Litwin-Kumar
Interest in biologically inspired alternatives to backpropagation is driven by the desire to both advance connections between deep learning and neuroscience and address backpropaga…
A Unified Theory of Early Visual Representations from Retina to Cortex through Anatomically Constrained Deep CNNs
Jack Lindsey, Samuel A. Ocko, Surya Ganguli +1
The visual system is hierarchically organized to process visual information in successive stages. Neural representations vary drastically across the first stages of visual processi…
Pre-training Attention Mechanisms
Jack Lindsey
Recurrent neural networks with differentiable attention mechanisms have had success in generative and classification tasks. We show that the classification performance of such mode…