Related papers: SPICEMixer - Netlist-Level Circuit Evolution
Recent progress on large language models (LLMs) has spurred interest in scaling up recommendation systems, yet two practical obstacles remain. First, training and serving cost on industrial Recommenders must respect strict latency bounds…
A new algorithm, termed subspace evolution and transfer (SET), is proposed for solving the consistent matrix completion problem. In this setting, one is given a subset of the entries of a low-rank matrix, and asked to find one low-rank…
Adders are fundamental building blocks in modern digital systems, and their performance, power, and area (PPA) directly impact system efficiency. Contemporary adders typically use parallel-prefix architectures with established PPA…
Spiking Neural Networks (SNNs) are widely deployed to solve complex pattern recognition, function approximation and image classification tasks. With the growing size and complexity of these networks, hardware implementation becomes…
Reverse engineering of gene regulatory networks presents one of the big challenges in systems biology. Gene regulatory networks are usually inferred from a set of single-gene over-expressions and/or knockout experiments. Functional…
Deep networks have achieved impressive results on a range of well-curated benchmark datasets. Surprisingly, their performance remains sensitive to perturbations that have little effect on human performance. In this work, we propose a novel…
Despite their empirical success, neural networks still have difficulty capturing compositional aspects of natural language. This work proposes a simple data augmentation approach to encourage compositional behavior in neural models for…
Recently, MLP-like vision models have achieved promising performances on mainstream visual recognition tasks. In contrast with vision transformers and CNNs, the success of MLP-like models shows that simple information fusion operations…
Quality-Diversity (QD) algorithms aim to discover diverse, high-performing solutions across behavioral niches. However, QD search often stagnates as incremental variation operators struggle to propagate building blocks across large…
Real networks exhibit nontrivial topological features such as heavy-tailed degree distribution, high clustering, and small-worldness. Researchers have developed several generative models for synthesizing artificial networks that are…
Identifying frequent subgraphs, also called network motifs, is crucial in analyzing and predicting properties of real-world networks. However, finding large commonly-occurring motifs remains a challenging problem not only due to its NP-hard…
Generative modeling of discrete variables is challenging yet crucial for applications in natural language processing and biological sequence design. We introduce the Shortlisting Model (SLM), a novel simplex-based diffusion model inspired…
Sparse matrix-matrix multiplication (SpGEMM) is a widely used kernel in various graph, scientific computing and machine learning algorithms. It is well known that SpGEMM is a memory-bound operation, and its peak performance is expected to…
Image Signal Processor (ISP) is a crucial component in digital cameras that transforms sensor signals into images for us to perceive and understand. Existing ISP designs always adopt a fixed architecture, e.g., several sequential modules…
Links in a practical network may have different functions, which makes the original network a combination of some functional subnetworks. Here, by a model of coupled oscillators, we investigate how such functional subnetworks are evolved…
The primary aim of automated performance improvement is to reduce the running time of programs while maintaining (or improving on) functionality. In this paper, Genetic Programming is used to find performance improvements in regular…
Recently, Graph Transformers have emerged as a promising solution to alleviate the inherent limitations of Graph Neural Networks (GNNs) and enhance graph representation performance. Unfortunately, Graph Transformers are computationally…
The modeling of conventional (deterministic) electronic circuits - ones consisting of transistors, resistors, capacitors, inductors, and other traditional electronic components - is a well-established subject. The cycle-to-cycle variability…
In this article, the problem of synthesizing switching controllers is considered through the synthesis of a "control certificate". Control certificates include control barrier and Lyapunov functions, which represent control strategies, and…
The similarity among samples and the discrepancy between clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from the inaccurate estimation of either feature similarity or semantic…