Tag
This paper proposes a learnable Dirichlet-process cache that allocates memory slots only for novel inputs, enabling efficient associative recall with a cache size proportional to distinct items rather than token count. It combines DP-means clustering with recurrent backbones, demonstrating effectiveness on associative recall benchmarks and real-world streams.
This paper presents a nonparametric Bayesian inverse reinforcement learning approach using a Dirichlet process prior to infer multiple latent reward types from expert demonstrations, implementing a collapsed Gibbs sampler with parallelization via Ray for scalability.
Introduces Neural Bayesian Sequential Routing (NBSR), a framework that models neural inference as sequential evidence accumulation over a DAG using Dirichlet-Categorical conjugate updates, enabling uncertainty quantification, early exiting, and resource-rational inference.