6 papers
Why Depth Matters in Parallelizable Sequence Models: A Lie Algebraic View
Gyuryang Heo, Timothy Ngotiaoco, Kazuki Irie +2
Scalable sequence models, such as Transformer variants and structured state-space models, often trade expressivity power for sequence-level parallelism, which enables efficient tra…
Fast weight programming and linear transformers: from machine learning to neurobiology
Kazuki Irie, Samuel J. Gershman
Recent advances in artificial neural networks for machine learning, and language modeling in particular, have established a family of recurrent neural network (RNN) architectures t…
Sequential-Parallel Duality in Prefix Scannable Models
Morris Yau, Sharut Gupta, Valerie Engelmayer +3
Modern neural sequence models are designed to meet the dual mandate of parallelizable training and fast sequential inference. Recent developments have given rise to various models,…
Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents
Zergham Ahmed, Kazuki Irie, Joshua B. Tenenbaum +2
Humans learn abstractions and use them to plan efficiently to quickly generalize across tasks -- an ability that remains challenging for state-of-the-art large language model (LLM)…
Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers
Kazuki Irie, Morris Yau, Samuel J. Gershman
We develop hybrid memory architectures for general-purpose sequence processing neural networks, that combine key-value memory using softmax attention (KV-memory) with fast weight m…
Key-value memory in the brain
Samuel J. Gershman, Ila Fiete, Kazuki Irie
Classical models of memory in psychology and neuroscience rely on similarity-based retrieval of stored patterns, where similarity is a function of retrieval cues and the stored pat…