Related papers: Adapting A Vector-Symbolic Memory for Lisp ACT-R

Memory retrieval in agentic large language model (LLM) systems is often treated as a static lookup problem, relying on flat vector search or fixed binary relational graphs. However, fixed graph structures cannot capture the varying…

Hyperdimensional computing (HDC), also known as vector symbolic architectures (VSA), is a computing framework used within artificial intelligence and cognitive computing that operates with distributed vector representations of large fixed…

Deep learning-based recommendation systems (e.g., DLRMs) are widely used AI models to provide high-quality personalized recommendations. Training data used for modern recommendation systems commonly includes categorical features taking on…

Vector symbolic architectures (VSAs) are a family of information representation techniques which enable composition, i.e., creating complex information structures from atomic vectors via binding and superposition, and have recently found…

How to learn highly compact yet effective sentence representation? Pre-trained language models have been effective in many NLP tasks. However, these models are often huge and produce large sentence embeddings. Moreover, there is a big…

Brain-inspired computing aims to mimic cognitive functions like associative memory, the ability to recall complete patterns from partial cues. Memristor technology offers promising hardware for such neuromorphic systems due to its potential…

We present NeuSymMS, an adaptive memory system that enables large language model (LLM) agents to learn, remember, and reason about users across sessions via a hybrid neuro-symbolic architecture. NeuSymMS couples neural fact extraction from…

Hyperdimensional computing (HDC) is an emerging computational framework that takes inspiration from attributes of neuronal circuits such as hyperdimensionality, fully distributed holographic representation, and (pseudo)randomness. When…

Recent progress has been made in using attention based encoder-decoder framework for image and video captioning. Most existing decoders apply the attention mechanism to every generated word including both visual words (e.g., "gun" and…

Multimodal Large Language Models (MLLMs) have achieved remarkable performance by aligning pretrained visual representations with the linguistic knowledge embedded in Large Language Models (LLMs). However, existing approaches typically rely…

Lexical and semantic matching capture different successful approaches to text retrieval and the fusion of their results has proven to be more effective and robust than either alone. Prior work performs hybrid retrieval by conducting lexical…

The hybrid opto-electronic correlator (HOC) architecture has been shown to be able to detect matches in a shift, scale, and rotation invariant (SSRI) manner by incorporating a polar Mellin transform (PMT) pre-processing step. Here we…

Comprehending extended audiovisual experiences remains challenging for computational systems, particularly temporal integration and cross-modal associations fundamental to human episodic memory. We introduce HippoMM, a computational…

We describe a new deep learning architecture for learning to rank question answer pairs. Our approach extends the long short-term memory (LSTM) network with holographic composition to model the relationship between question and answer…

Large-capacity Content Addressable Memory (CAM) is a key element in a wide variety of applications. The inevitable complexities of scaling MOS transistors introduce a major challenge in the realization of such systems. Convergence of…

While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current memory systems enable basic storage and retrieval but lack…

Due to the rapid advancements of sensory and computing technology, multi-modal data sources that represent the same pattern or phenomenon have attracted growing attention. As a result, finding means to explore useful information from these…

Analog Compute-in-Memory (CiM) accelerators are increasingly recognized for their efficiency in accelerating Deep Neural Networks (DNN). However, their dependence on Analog-to-Digital Converters (ADCs) for accumulating partial sums from…

Memory-augmented Large Language Models (LLMs) have demonstrated remarkable consistency during prolonged dialogues by storing relevant memories and incorporating them as context. Such memory-based personalization is also key in on-device…

We introduce \emph{Adaptive RAG Memory} (ARM), a retrieval-augmented generation (RAG) framework that replaces a static vector index with a \emph{dynamic} memory substrate governed by selective remembrance and decay. Frequently retrieved…