4 papers
When RL Suppresses Its Own Vocabulary: Recovering Reasoning Diversity in Puzzle-to-Math Transfer
Mayug Maniparambil, Arjun Karuvally, Terrence Sejnowski +1
Reinforcement learning using verifiable rewards (RLVR) improves LLM reasoning, but the conditions under which it transfers across domains -- and why it does so -- remain under-expl…
NeuroAI and Beyond: Bridging Between Advances in Neuroscience and ArtificialIntelligence
Anthony Zador, Jean-Marc Fellous, Terrence Sejnowski +28
Neuroscience and Artificial Intelligence (AI) have made impressive progress in recent years but remain only loosely interconnected. Based on a workshop convened by the National Sci…
EEG Foundation Challenge: From Cross-Task to Cross-Subject EEG Decoding
Bruno Aristimunha, Dung Truong, Pierre Guetschel +17
Current electroencephalogram (EEG) decoding models are typically trained on small numbers of subjects performing a single task. Here, we introduce a large-scale, code-submission-ba…
The Memory Paradox: Why Our Brains Need Knowledge in an Age of AI
Barbara Oakley, Michael Johnston, Ken-Zen Chen +2
In the age of generative AI and ubiquitous digital tools, human cognition faces a structural paradox: as external aids become more capable, internal memory systems risk atrophy. Dr…