Interested in cognition and artificial intelligence. Researcher at Anthropic; previously DeepMind, cognitive science at Stanford. Posts are mine. lampinen.github.io
What should we make of recent language model advancements in mathematics? In my new post, I reflect on long-standing cognitive debates about symbols and neural networks in light of this progress. infinitefaculty.substack.com/p/symbols-ne...
Symbols, neural networks, and mathematical intelligenceSome reflections on connectionism and the basis of higher-level cognitioninfinitefaculty.substack.comPleased to share that this work is now published in TMLR! openreview.net/forum?id=RuW...
Latent learning: episodic memory complements parametric learning by...When do machine learning systems fail to generalize, and what mechanisms could improve their generalization? Here, we draw inspiration from cognitive science to argue that one weakness of...openreview.netAndrew LampinenWhy does AI sometimes fail to generalize, and what might help? In a new paper (arxiv.org/abs/2509.16189), we highlight the latent learning gap — which unifies findings from language modeling to agent navigation — and suggest that episodic memory complements parametric learning to bridge it. Thread:
What are the real problems to be solved in continual learning? In my latest post, I tackle this question — reviewing where I think the field went astray in the past, how language models changed things, and where the real challenges remain. infinitefaculty.substack.com/p/what-are-t...
What are the real problems of continual learning?Reflections on catastrophic interference, plasticity, and learning for the future in the era of large language modelsinfinitefaculty.substack.comWe've updated the preprint of our Naturalistic Computational Cognitive Science paper (arxiv.org/abs/2502.20349) — we've tried to clarify and streamline the arguments, and added some new examples: 1/5
Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behaviorHow can cognitive science build generalizable theories that span the full scope of natural situations and behaviors? We argue that progress in Artificial Intelligence (AI) offers timely opportunities ...arxiv.orgWhen and how can test-time thinking allow models to use information latent in their training data? What are the benefits and tradeoffs relative to other solutions like synthetic data augmentation? Pleased to share (after a long delay) an exploration of these issues: arxiv.org/abs/2604.01430 thread:
Improving Latent Generalization Using Test-time ComputeLanguage Models (LMs) exhibit two distinct mechanisms for knowledge acquisition: in-weights learning (i.e., encoding information within the model weights) and in-context learning (ICL). Although these...arxiv.orgPleased to share that our paper "Representation Biases: Variance is Not Always a Good Proxy for Importance" is now out as Theory/New Concepts paper in eNeuro! www.eneuro.org/content/13/3... 1/
Representation Biases: Variance Is Not Always a Good Proxy for ImportanceA central approach in neuroscience is to analyze neural representations as a means to understand a system's function, through the use of methods like principal component analysis, regression, and repr...www.eneuro.org