Related papers: Beyond LLMs, Sparse Distributed Memory, and Neurom…
Vector-HaSH and the Tolman-Eichenbaum Machine (TEM) propose the hippocampal-entorhinal circuit factorizes memory via a grid-cell scaffold for compositional replay. Concurrently, human iEEG shows sharp-wave ripples gate recall and multi-hop…
Hyperdimensional computing (HDC) is a brain-inspired paradigm valued for its noise robustness, parallelism, energy efficiency, and low computational overhead. Hardware accelerators are being explored to further enhance their performance,…
Hyperdimensional Computing (HDC) offers a computationally efficient paradigm for neuromorphic learning. Yet, it lacks rigorous uncertainty quantification, leading to open decision boundaries and, consequently, vulnerability to outliers,…
Hyperdimensional computing (HDC) is an emerging learning paradigm that computes with high dimensional binary vectors. It is attractive because of its energy efficiency and low latency, especially on emerging hardware -- but HDC suffers from…
Large Language Models (LLMs) exhibit remarkable capabilities but suffer from apparent precision loss, reframed here as information spreading. This reframing shifts the problem from computational precision to an information-theoretic…
Hyperdimensional Computing (HDC) is a brain-inspired computing paradigm that represents and manipulates information using high-dimensional vectors, called hypervectors (HV). Traditional HDC methods, while robust to noise and inherently…
Hyperdimensional computing (HDC), utilizing a parallel computing paradigm and efficient learning algorithm, is well-suited for resource-constrained artificial intelligence (AI) applications, such as in edge devices. In-memory computing…
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…
Brain-inspired hyperdimensional computing (HDC) is continuously gaining remarkable attention. It is a promising alternative to traditional machine-learning approaches due to its ability to learn from little data, lightweight implementation,…
Mechanistic interpretability seeks to reverse-engineer neural network computations into human-understandable algorithms, yet extracting sparse computational circuits from billion-parameter language models remains challenging due to…
Data encoding is a fundamental step in emerging computing paradigms, particularly in stochastic computing (SC) and hyperdimensional computing (HDC), where it plays a crucial role in determining the overall system performance and hardware…
Multiphoton photoreduction enables high-fidelity fabrication of complex 3D microstructures, yet reliable process-structure-property (PSP) prediction remains difficult because the available data are sparse, heterogeneous, and…
Graph classification is a fundamental task in domains ranging from molecular property prediction to materials design. While graph neural networks (GNNs) achieve strong performance by learning expressive representations via message passing,…
Across a variety of scientific disciplines, sparse inverse covariance estimation is a popular tool for capturing the underlying dependency relationships in multivariate data. Unfortunately, most estimators are not scalable enough to handle…
Graphical model estimation from multi-omics data requires a balance between statistical estimation performance and computational scalability. We introduce a novel pseudolikelihood-based graphical model framework that reparameterizes the…
We introduce a curriculum learning algorithm, Variational Automatic Curriculum Learning (VACL), for solving challenging goal-conditioned cooperative multi-agent reinforcement learning problems. We motivate our paradigm through a variational…
Hyperdimensional Computing (HDC) is an emerging computational paradigm for representing compositional information as high-dimensional vectors, and has a promising potential in applications ranging from machine learning to neuromorphic…
Hyperdimensional Computing (HDC) represents data using extremely high-dimensional, low-precision vectors, termed hypervectors (HVs), and performs learning and inference through lightweight, noise-tolerant operations. However, the high…
The Internet of Things (IoT) has facilitated many applications utilizing edge-based machine learning (ML) methods to analyze locally collected data. Unfortunately, popular ML algorithms often require intensive computations beyond the…
Large language models (LLMs) have demonstrated remarkable proficiency in a wide range of natural language processing applications. However, the high energy and latency overhead induced by the KV cache limits the edge deployment, especially…