# Predictive Associative Memory: Retrieval Beyond Similarity Through Temporal Co-occurrence

arXiv: https://arxiv.org/abs/2602.11322 · HTML: https://mlsanity.com/paper/2602.11322/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Builds on (most cited first, 21 of 21)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Hopfield Networks is All You Need](https://mlsanity.com/paper/2008.02217/) (2020)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Successor Features for Transfer in Reinforcement Learning](https://mlsanity.com/paper/1606.05312/) (2016)
- [Dense Associative Memory for Pattern Recognition](https://mlsanity.com/paper/1606.01164/) (2016)
- [Query Rewriting for Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2305.14283/) (2023)
- [Large Associative Memory Problem in Neurobiology and Machine Learning](https://mlsanity.com/paper/2008.06996/) (2020)
- [Deep Successor Reinforcement Learning](https://mlsanity.com/paper/1606.02396/) (2016)
- [Large Language Model Reasoning Failures](https://mlsanity.com/paper/2602.06176/) (2026)

## Built on by (most cited first, 3 of 3)

- [From Topic to Transition Structure: Unsupervised Concept Discovery at Corpus Scale via Predictive Associative Memory](https://mlsanity.com/paper/2603.18420/) (2026)
- [Beyond Expression Similarity: Contrastive Learning Recovers Functional Gene Associations from Protein Interaction Structure](https://mlsanity.com/paper/2603.20955/) (2026)
- [vstash: Local-First Hybrid Retrieval with Adaptive Fusion for LLM Agents](https://mlsanity.com/paper/2604.15484/) (2026)

## Abstract (arXiv)

Current approaches to memory in neural systems rely on similarity-based retrieval: given a query, find the most representationally similar stored state. This assumption -- that useful memories are similar memories -- fails to capture a fundamental property of biological memory: association through temporal co-occurrence. We propose Predictive Associative Memory (PAM), an architecture in which a JEPA-style predictor, trained on temporal co-occurrence within a continuous experience stream, learns to navigate the associative structure of an embedding space. We introduce an Inward JEPA that operates over stored experience (predicting associatively reachable past states) as the complement to the standard Outward JEPA that operates over incoming sensory data (predicting future states). We evaluate PAM as an associative recall system -- testing faithfulness of recall for experienced associations -- rather than as a retrieval system evaluated on generalisation to unseen associations. On a synthetic benchmark, the predictor's top retrieval is a true temporal associate 97% of the time (Association Precision@1 = 0.970); it achieves cross-boundary Recall@20 = 0.421 where cosine similarity scores zero; and it separates experienced-together from never-experienced-together states with a discrimination AUC of 0.916 (cosine: 0.789). Even restricted to cross-room pairs where embedding similarity is uninformative, the predictor achieves AUC = 0.849 (cosine: 0.503, chance). A temporal shuffle control confirms the signal is genuine temporal co-occurrence structure, not embedding geometry: shuffling collapses cross-boundary recall by 90%, replicated across training seeds. All results are stable across seeds (SD < 0.006) and query selections (SD ≤ 0.012).