4 papers
Constant-Memory Recall: Learned Associations in a Fixed Matrix State
Samuel Larson
Fixed-size recurrent memory limits storage growth during inference, but successful recall depends on the task and training. We study a small DeltaNet variant with fixed token-speci…
When the Gradient Sees Rank: Provable Necessity, Causal Recruitment, and Composition in Trained Matrix Memories
Samuel Larson
Can gradient-based training learn the rank needed to store and compose associations in a matrix memory? In our earlier study, we used a matrix-augmented reasoner on a task that adm…
The Rank the Task Demands: A Causal Rank Law for Matrix Memories Trained on Group Composition
Samuel Larson
Matrix-valued memories make rank the natural budget of a learned representation: the number of independent directions a state spans bounds what it can bind, compose, and track. We…
The Gradient Does Not See Rank: Rank-Indifference in Matrix-CODI on ProsQA
Samuel Larson
Continuous chain-of-thought models compress reasoning into latent tokens. Matrix-valued variants, which route each latent token through a d x d matrix bottleneck, introduce rank as…