Tootfinder

Transversal STAR architecture for megaquop-scale quantum simulation with neutral atoms
Refaat Ismail, I-Chi Chen, Chen Zhao, Ronen Weiss, Fangli Liu, Hengyun Zhou, Sheng-Tao Wang, Andrew Sornborger, Milan Kornja\v{c}a
https://arxiv.org/abs/2509.18294

Polyharmonic Cascade
Yuriy N. Bakhvalov
https://arxiv.org/abs/2512.17671 https://arxiv.org/pdf/2512.17671 https://arxiv.org/html/2512.17671
arXiv:2512.17671v1 Announce Type: new
Abstract: This paper presents a deep machine learning architecture, the "polyharmonic cascade" -- a sequence of packages of polyharmonic splines, where each layer is rigorously derived from the theory of random functions and the principles of indifference. This makes it possible to approximate nonlinear functions of arbitrary complexity while preserving global smoothness and a probabilistic interpretation. For the polyharmonic cascade, a training method alternative to gradient descent is proposed: instead of directly optimizing the coefficients, one solves a single global linear system on each batch with respect to the function values at fixed "constellations" of nodes. This yields synchronized updates of all layers, preserves the probabilistic interpretation of individual layers and theoretical consistency with the original model, and scales well: all computations reduce to 2D matrix operations efficiently executed on a GPU. Fast learning without overfitting on MNIST is demonstrated.
toXiv_bot_toot

Exploiting ID-Text Complementarity via Ensembling for Sequential Recommendation
Liam Collins, Bhuvesh Kumar, Clark Mingxuan Ju, Tong Zhao, Donald Loveland, Leonardo Neves, Neil Shah
https://arxiv.org/abs/2512.17820 https://arxiv.org/pdf/2512.17820 https://arxiv.org/html/2512.17820
arXiv:2512.17820v1 Announce Type: new
Abstract: Modern Sequential Recommendation (SR) models commonly utilize modality features to represent items, motivated in large part by recent advancements in language and vision modeling. To do so, several works completely replace ID embeddings with modality embeddings, claiming that modality embeddings render ID embeddings unnecessary because they can match or even exceed ID embedding performance. On the other hand, many works jointly utilize ID and modality features, but posit that complex fusion strategies, such as multi-stage training and/or intricate alignment architectures, are necessary for this joint utilization. However, underlying both these lines of work is a lack of understanding of the complementarity of ID and modality features. In this work, we address this gap by studying the complementarity of ID- and text-based SR models. We show that these models do learn complementary signals, meaning that either should provide performance gain when used properly alongside the other. Motivated by this, we propose a new SR method that preserves ID-text complementarity through independent model training, then harnesses it through a simple ensembling strategy. Despite this method's simplicity, we show it outperforms several competitive SR baselines, implying that both ID and text features are necessary to achieve state-of-the-art SR performance but complex fusion architectures are not.
toXiv_bot_toot

FHEON: A Configurable Framework for Developing Privacy-Preserving Neural Networks Using Homomorphic Encryption
Nges Brian Njungle, Eric Jahns, Michel A. Kinsy
https://arxiv.org/abs/2510.03996

FHEON: A Configurable Framework for Developing Privacy-Preserving Neural Networks Using Homomorphic Encryption
The widespread adoption of Machine Learning as a Service raises critical privacy and security concerns, particularly about data confidentiality and trust in both cloud providers and the machine learning models. Homomorphic Encryption (HE) has emerged as a promising solution to this problems, allowing computations on encrypted data without decryption. Despite its potential, existing approaches to integrate HE into neural networks are often limited to specific architectures, leaving a wide gap in…

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights
Sangmin Bae, Bilge Acun, Haroun Habeeb, Seungyeon Kim, Chien-Yu Lin, Liang Luo, Junjie Wang, Carole-Jean Wu
https://arxiv.org/abs/2510.04800

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights
Recent progress in large language models demonstrates that hybrid architectures--combining self-attention mechanisms with structured state space models like Mamba--can achieve a compelling balance between modeling quality and computational efficiency, particularly for long-context tasks. While these hybrid models show promising performance, systematic comparisons of hybridization strategies and analyses on the key factors behind their effectiveness have not been clearly shared to the community.…

Multi-port programmable silicon photonics using low-loss phase change material Sb$_2$Se$_3$
Thomas W. Radford, Idris A Ajia, Latif Rozaqi, Priya Deoli, Xingzhao Yan, Mehdi Banakar, David J Thomson, Ioannis Zeimpekis, Alberto Politi, Otto L. Muskens
https://arxiv.org/abs/2511.18205 https://arxiv.org/pdf/2511.18205 https://arxiv.org/html/2511.18205
arXiv:2511.18205v1 Announce Type: new
Abstract: Reconfigurable photonic devices are rapidly emerging as a cornerstone of next generation optical technologies, with wide ranging applications in quantum simulation, neuromorphic computing, and large-scale photonic processors. A central challenge in this field is identifying an optimal platform to enable compact, efficient, and scalable reconfigurability. Optical phase-change materials (PCMs) offer a compelling solution by enabling non-volatile, reversible tuning of optical properties, compatible with a wide range of device platforms and current CMOS technologies. In particular, antimony tri-selenide ($\text{Sb}_{2}\text{Se}_{3}$) stands out for its ultra low-loss characteristics at telecommunication wavelengths and its reversible switching. In this work, we present an experimental platform capable of encoding multi-port operations onto the transmission matrix of a compact multimode interferometer architecture on standard 220~nm silicon photonics using \textit{in-silico} designed digital patterns. The multi-port devices are clad with a thin film of $\text{Sb}_{2}\text{Se}_{3}$, which can be optically addressed using direct laser writing to provide local perturbations to the refractive index. A range of multi-port geometries from 2$\times$2 up to 5$\times$5 couplers are demonstrated, achieving simultaneous control of up to 25 matrix elements with programming accuracy of 90% relative to simulated patterns. Patterned devices remain stable with consistent optical performance across the C-band wavelengths. Our work establishes a pathway towards the development of large scale PCM-based reconfigurable multi-port devices which will allow implementing matrix operations on three orders of magnitude smaller areas than interferometer meshes.
toXiv_bot_toot

CAPSim: A Fast CPU Performance Simulator Using Attention-based Predictor
Buqing Xu, Jianfeng Zhu, Yichi Zhang, Qinyi Cai, Guanhua Li, Shaojun Wei, Leibo Liu
https://arxiv.org/abs/2510.10484

CAPSim: A Fast CPU Performance Simulator Using Attention-based Predictor
CPU simulators are vital for computer architecture research, primarily for estimating performance under different programs. This poses challenges for fast and accurate simulation of modern CPUs, especially in multi-core systems. Modern CPU peformance simulators such as GEM5 adopt the cycle-accurate and event-driven approach, which is timeconsuming to simulate the extensive microarchitectural behavior of a real benchmark running on out-of-order CPUs. Recently, machine leaning based approach has …

Confidentiality-Preserving Verifiable Business Processes through Zero-Knowledge Proofs
Jannis Kiesel, Jonathan Heiss
https://arxiv.org/abs/2509.20300 https://

Confidentiality-Preserving Verifiable Business Processes through Zero-Knowledge Proofs
Ensuring the integrity of business processes without disclosing confidential business information is a major challenge in inter-organizational processes. This paper introduces a zero-knowledge proof (ZKP)-based approach for the verifiable execution of business processes while preserving confidentiality. We integrate ZK virtual machines (zkVMs) into business process management engines through a comprehensive system architecture and a prototypical implementation. Our approach supports chained ver…

CAPSim: A Fast CPU Performance Simulator Using Attention-based Predictor
Buqing Xu, Jianfeng Zhu, Yichi Zhang, Qinyi Cai, Guanhua Li, Shaojun Wei, Leibo Liu
https://arxiv.org/abs/2510.10484

CAPSim: A Fast CPU Performance Simulator Using Attention-based Predictor
CPU simulators are vital for computer architecture research, primarily for estimating performance under different programs. This poses challenges for fast and accurate simulation of modern CPUs, especially in multi-core systems. Modern CPU peformance simulators such as GEM5 adopt the cycle-accurate and event-driven approach, which is timeconsuming to simulate the extensive microarchitectural behavior of a real benchmark running on out-of-order CPUs. Recently, machine leaning based approach has …

Probing a theoretical framework for a Photonic Extreme Learning Machine
Vicente Rocha, Duarte Silva, Felipe C. Moreira, Catarina S. Monteiro, Tiago D. Ferreira, Nuno A. Silva
https://arxiv.org/abs/2510.02918

Probing a theoretical framework for a Photonic Extreme Learning Machine
The development of computing paradigms alternative to von Neumann architectures has recently fueled significant progress in novel all-optical processing solutions. In this work, we investigate how the coherence properties can be exploited for computing by expanding information onto a higher-dimensional space in the photonic extreme learning machine framework. A theoretical framework is provided based on the transmission matrix formalism, mapping the input plane onto the output camera plane, res…