Related papers: WorldDB: A Vector Graph-of-Worlds Memory Engine wi…

We introduce MemoriesDB, a unified data architecture designed to avoid decoherence across time, meaning, and relation in long-term computational memory. Each memory is a time-semantic-relational entity-a structure that simultaneously…

Retrieval-Augmented Generation (RAG) has established itself as the standard paradigm for grounding Large Language Models (LLMs) in domain-specific, up-to-date data. However, the prevailing architecture for RAG has evolved into a complex,…

Modern retrieval-augmented generation (RAG) systems treat vector embeddings as static, context-free artifacts: an embedding has no notion of when it was created, how trustworthy its source is, or which other embeddings depend on it. This…

Long-term memory is essential for conversational agents to maintain coherence, track persistent tasks, and provide personalized interactions across extended dialogues. However, existing approaches as Retrieval-Augmented Generation (RAG) and…

We introduce a new model, the Recurrent Entity Network (EntNet). It is equipped with a dynamic long-term memory which allows it to maintain and update a representation of the state of the world as it receives new data. For language…

Autoregressive video diffusion models have enabled real-time, action-conditioned world generation. However, sustaining a persistent world, where revisiting a previously seen viewpoint yields consistent content, remains an open problem. Full…

Text-Attributed Graphs (TAGs) augment graph structures with natural language descriptions, facilitating detailed depictions of data and their interconnections across various real-world settings. However, existing TAG datasets predominantly…

Relational databases store much of the world's structured information, and they are essential for driving complex predictive applications. However, deep learning progress on relational data remains limited, as conventional approaches…

Modeling evolving interactions among entities is critical in many real-world tasks. For example, predicting driver maneuvers in traffic requires tracking how neighboring vehicles accelerate, brake, and change lanes relative to one another…

Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that demand global comprehension and intensive reasoning. Although many RAG systems incorporate a…

Large language models still struggle with reliable long-term conversational memory: simply enlarging context windows or applying naive retrieval often introduces noise and destabilizes responses. We present APEX-MEM, a conversational memory…

Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchmarks, which narrowly focus on traditional passage retrieval and fail to assess models'…

Multimodal large language models are increasingly deployed as long-horizon agents, where memory must do more than recall: it must track an evolving world, revise what has gone stale, and surface the right evidence at decision time. Existing…

The rapid evolution of Large Language Models (LLMs) towards long-context reasoning and sparse architectures has pushed memory requirements far beyond the capacity of individual device HBM. While emerging supernode architectures offer…

In this systems paper, we present MillenniumDB: a novel graph database engine that is modular, persistent, and open source. MillenniumDB is based on a graph data model, which we call domain graphs, that provides a simple abstraction upon…

Recent advances in video large language models have demonstrated strong capabilities in understanding short clips. However, scaling them to hours- or days-long videos remains highly challenging due to limited context capacity and the loss…

Many problems such as node classification and link prediction in network data can be solved using graph embeddings. However, it is difficult to use graphs to capture non-binary relations such as communities of nodes. These kinds of complex…

Lifelong interactive agents are expected to assist users over months or years, which requires continually writing long term memories while retrieving the right evidence for each new query under fixed context and latency budgets. Existing…

This paper introduces RG (Relational Genetic) model, a revised relational model to represent graph-structured data in RDBMS while preserving its topology, for efficiently and effectively extracting data in different formats from disparate…

This paper presents a hybrid architecture for intelligent systems in which large language models (LLMs) are extended with an external ontological memory layer. Instead of relying solely on parametric knowledge and vector-based retrieval…