Selected work

Representative Papers

Sparse Quantum Voxel Encoding for Readout-Efficient Molecular Geometry Reconstruction on NISQ Devices

Jul 29, 2026

This work addresses the challenge of efficiently reconstructing molecular geometries on noisy intermediate-scale quantum (NISQ) devices, where conventional full-state tomography incurs prohibitive exponential measurement overhead. The authors propose a sparse voxel encoding scheme that discretizes molecular space into a three-dimensional voxel grid, mapping atomic positions and species to a single computational basis state and thereby constructing a sparse equal-amplitude superposition. This formulation recasts geometry reconstruction as a support recovery problem under computational-basis sampling. The approach reduces measurement complexity from exponential to $O(A \log A)$, where $A$ is the number of atoms. Demonstrated on IBM’s 156-qubit Kingston device, the method reconstructs the discretized geometry of a 10-atom ethylamine molecule with high recall using only approximately $10^2$ measurements, significantly enhancing readout efficiency on NISQ hardware.

0 citationsRead paper

TOMOYO Linux: A Mandatory Access Control Method Based on Application Execution State

Jun 06, 2026

Traditional access control mechanisms rely solely on static bindings between applications and files, neglecting application intent and operational context, thereby offering limited protection against malicious actions and user errors. This work proposes a mandatory access control approach grounded in application execution history and semantic intent, introducing program runtime state and contextual semantics into access decisions for the first time and thus transcending the limitations of classical subject-object models. A state-aware policy enforcement engine is implemented as a Linux kernel module, integrated with execution path tracking to construct a fine-grained, context-sensitive access control framework. The effectiveness of this approach is validated through a prototype implementation in TOMOYO Linux. Experimental results demonstrate a significant reduction in security risks arising from both malicious accesses and inadvertent user operations.

0 citationsRead paper

A Workflow-Oriented Framework for Asynchronous Human-AI Collaboration in Hybrid and Compute-Intensive HPC Environments

May 05, 2026

This work addresses the challenge of real-time human oversight in high-performance computing (HPC) environments, where manual intervention is often impractical and can lead to resource waste and delayed decisions. To overcome this, the paper introduces the first workflow-oriented asynchronous human-in-the-loop framework, which enables non-blocking collaboration by pausing at designated checkpoints to solicit human input while allowing underlying tasks to continue execution across hybrid infrastructures—spanning HPC systems, on-premises clusters, and cloud platforms. The framework integrates with the SLURM scheduler, supports both containerized and native workloads, and leverages a cross-platform workflow engine combined with checkpointing technology. Experiments on systems such as MareNostrum 5 demonstrate significant improvements in portability, computational efficiency, and supervisory control, particularly benefiting high-stakes scenarios requiring flexible human–machine coordination.

0 citationsRead paper

Scalable Sequential Recommendation under Latency and Memory Constraints

Jan 13, 2026

This work addresses the challenge of efficiently modeling long user behavioral sequences under stringent memory and latency constraints. The authors propose HoloMambaRec, a novel architecture that integrates holographic reduced representations with selective state space models (Mamba). By employing holographic embeddings to unify item and attribute information and leveraging a shallow Mamba encoder, the model achieves linear-time sequence modeling and constant-time inference, enabling temporal bundling and inference compression. Experimental results demonstrate that HoloMambaRec matches the performance of GRU4Rec and outperforms SASRec on Amazon Beauty and MovieLens-1M datasets, while substantially reducing memory consumption—making it particularly suitable for resource-constrained scenarios with as few as 10 training epochs.

0 citationsRead paper

An SLO Driven and Cost-Aware Autoscaling Framework for Kubernetes

Dec 29, 2025

Kubernetes’ native autoscaling mechanisms—relying on reactive decision-making, underutilizing application-layer signals, and employing opaque control logic—frequently violate SLOs and waste resources. To address these limitations, we propose an AIOps-driven, multi-signal collaborative autoscaling framework that jointly optimizes for SLO compliance, cost constraints, and lightweight time-series demand forecasting. This work establishes the first SLO-first, cost-aware, and safety-guaranteed unified control paradigm with inherent interpretability. By integrating multidimensional metrics into a unified model and embedding a closed-loop feedback controller, our approach ensures transparent scaling decisions and auditable operational traces. Experimental evaluation demonstrates a 31% reduction in SLO violation duration, a 24% acceleration in scaling responsiveness, and an 18% decrease in infrastructure costs—all while preserving system stability and full operational traceability.

0 citationsRead paper

Recent publications

Latest Papers

Sparse Quantum Voxel Encoding for Readout-Efficient Molecular Geometry Reconstruction on NISQ Devices

Jul 29, 2026

This work addresses the challenge of efficiently reconstructing molecular geometries on noisy intermediate-scale quantum (NISQ) devices, where conventional full-state tomography incurs prohibitive exponential measurement overhead. The authors propose a sparse voxel encoding scheme that discretizes molecular space into a three-dimensional voxel grid, mapping atomic positions and species to a single computational basis state and thereby constructing a sparse equal-amplitude superposition. This formulation recasts geometry reconstruction as a support recovery problem under computational-basis sampling. The approach reduces measurement complexity from exponential to $O(A \log A)$, where $A$ is the number of atoms. Demonstrated on IBM’s 156-qubit Kingston device, the method reconstructs the discretized geometry of a 10-atom ethylamine molecule with high recall using only approximately $10^2$ measurements, significantly enhancing readout efficiency on NISQ hardware.

0 citationsRead paper

TOMOYO Linux: A Mandatory Access Control Method Based on Application Execution State

Jun 06, 2026

Traditional access control mechanisms rely solely on static bindings between applications and files, neglecting application intent and operational context, thereby offering limited protection against malicious actions and user errors. This work proposes a mandatory access control approach grounded in application execution history and semantic intent, introducing program runtime state and contextual semantics into access decisions for the first time and thus transcending the limitations of classical subject-object models. A state-aware policy enforcement engine is implemented as a Linux kernel module, integrated with execution path tracking to construct a fine-grained, context-sensitive access control framework. The effectiveness of this approach is validated through a prototype implementation in TOMOYO Linux. Experimental results demonstrate a significant reduction in security risks arising from both malicious accesses and inadvertent user operations.

0 citationsRead paper

A Workflow-Oriented Framework for Asynchronous Human-AI Collaboration in Hybrid and Compute-Intensive HPC Environments

May 05, 2026

This work addresses the challenge of real-time human oversight in high-performance computing (HPC) environments, where manual intervention is often impractical and can lead to resource waste and delayed decisions. To overcome this, the paper introduces the first workflow-oriented asynchronous human-in-the-loop framework, which enables non-blocking collaboration by pausing at designated checkpoints to solicit human input while allowing underlying tasks to continue execution across hybrid infrastructures—spanning HPC systems, on-premises clusters, and cloud platforms. The framework integrates with the SLURM scheduler, supports both containerized and native workloads, and leverages a cross-platform workflow engine combined with checkpointing technology. Experiments on systems such as MareNostrum 5 demonstrate significant improvements in portability, computational efficiency, and supervisory control, particularly benefiting high-stakes scenarios requiring flexible human–machine coordination.

0 citationsRead paper

Scalable Sequential Recommendation under Latency and Memory Constraints

Jan 13, 2026

This work addresses the challenge of efficiently modeling long user behavioral sequences under stringent memory and latency constraints. The authors propose HoloMambaRec, a novel architecture that integrates holographic reduced representations with selective state space models (Mamba). By employing holographic embeddings to unify item and attribute information and leveraging a shallow Mamba encoder, the model achieves linear-time sequence modeling and constant-time inference, enabling temporal bundling and inference compression. Experimental results demonstrate that HoloMambaRec matches the performance of GRU4Rec and outperforms SASRec on Amazon Beauty and MovieLens-1M datasets, while substantially reducing memory consumption—making it particularly suitable for resource-constrained scenarios with as few as 10 training epochs.

0 citationsRead paper

An SLO Driven and Cost-Aware Autoscaling Framework for Kubernetes

Dec 29, 2025

Kubernetes’ native autoscaling mechanisms—relying on reactive decision-making, underutilizing application-layer signals, and employing opaque control logic—frequently violate SLOs and waste resources. To address these limitations, we propose an AIOps-driven, multi-signal collaborative autoscaling framework that jointly optimizes for SLO compliance, cost constraints, and lightweight time-series demand forecasting. This work establishes the first SLO-first, cost-aware, and safety-guaranteed unified control paradigm with inherent interpretability. By integrating multidimensional metrics into a unified model and embedding a closed-loop feedback controller, our approach ensures transparent scaling decisions and auditable operational traces. Experimental evaluation demonstrates a 31% reduction in SLO violation duration, a 24% acceleration in scaling responsiveness, and an 18% decrease in infrastructure costs—all while preserving system stability and full operational traceability.

0 citationsRead paper