associative-recall

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 work proposes orthogonalizing the memory matrix of mLSTM recurrent models to improve their performance on noisy associative recall tasks. Experiments show that using Newton-Schulz iterations for read-only orthogonalization enhances validation accuracy compared to baseline mLSTM.

T-Mem is a new long-term conversational memory architecture that enables both descriptive and associative recall, covering scenarios where query and memory share surface features and those where they are connected by latent semantic arcs. It reaches state-of-the-art on the LoCoMo and LoCoMo-Plus benchmarks.

This paper introduces generic triple-latent recurrent models that compress token pair interactions into a latent state, and a gated associative retrieval variant that improves exact recall. The hybrid model outperforms Transformers on byte-level WikiText-2 and a tokenized language benchmark, achieving up to 41.9% associative recall versus 25%.