58 papers
This paper proposes HGT-Scheduler, a deep reinforcement learning framework that utilizes Heterogeneous Graph Transformers to explicitly model the distinct edge semantics of the Job Shop Scheduling Problem, thereby outperforming homogeneous graph baselines on benchmark instances by capturing type-specific relational patterns through edge-type-dependent attention mechanisms.
This paper argues that resilience must be established as a fundamental design constraint in integrated classical-quantum computing systems by developing new quantitative models and metrics, drawing inspiration from civil engineering to accurately assess the cost-benefit ratios of system improvements and their cascading impacts on end-user value.
This report summarizes the outcomes of the September 2024 NSF Workshop on Algorithm-Hardware Co-design for Medical Applications, outlining a strategic roadmap and key recommendations to advance next-generation medical technologies across four thematic areas through fundamental shifts in design, validation, and infrastructure.
This paper challenges the optimistic narrative of fully automated AI auditing by demonstrating that EVMbench's results are compromised by data contamination and narrow evaluation, revealing that current AI agents lack the stability and end-to-end exploitation capabilities to replace human auditors in smart contract security.
This study utilizes advanced computational simulations to demonstrate that incorporating realistic vascular factors, such as non-uniform flow and red blood cell interactions, significantly reduces the detection probability of early-stage cancer biomarkers by intravascular nanomachines, with capillaries consistently showing the highest detection efficiency across various nanomachine sizes.
This paper demonstrates that LoRA fine-tuning of compact LLM backbones significantly enhances voice cloning performance in terms of perceptual quality, speaker fidelity, and signal-to-noise ratio, provided the training data possesses sufficient acoustic diversity.
This paper presents a human-centred system design that leverages conversational AI and function-calling capabilities to enable natural language querying and visual-spatial exploration of nearly 1.7 million digitised natural history specimen records at the Australian Museum, overcoming the limitations of traditional keyword-based search tools.
This paper introduces a novel single-layer Quantum Neural Network that leverages the Standard Recursive Block Basis (SRBB) and Lie algebraic properties to efficiently approximate arbitrary unitary evolutions with an exponentially reduced CNOT count, demonstrating its effectiveness through simulations on up to 6 qubits and validation on real quantum hardware.
This paper presents a reference architecture and roadmap for Quantum-Centric Supercomputing (QCSC) systems that integrate quantum, GPU, and CPU resources to overcome current isolation challenges and enable seamless, high-performance hybrid workflows across three evolutionary phases.
This paper introduces Hybridlane, an open-source software development kit that enables unified, scalable programming of hybrid continuous-discrete variable quantum circuits through automatic wire type inference, backend-agnostic gate semantics, and compatibility with both classical simulators and ion trap hardware.
This paper presents a systematic literature review of 80 studies on "systems of twinned systems," a paradigm that integrates the System of Systems and Digital Twin concepts to address modern engineering complexity, resulting in a new classification framework compatible with existing theories.
This paper proposes a scalable digital compute-in-memory SRAM-based Ising machine that reformulates binary neural network robustness verification as a QUBO problem, leveraging imperfect solutions to efficiently detect adversarial perturbations while achieving significant improvements in convergence speed and power efficiency compared to conventional CPU implementations.
This paper proposes Belief-Adaptive MAP and Soft BA-MAP detectors that explicitly account for state-dependent noise variance in molecular communication channels, demonstrating significant throughput improvements over conventional methods through simulations and information-theoretic analysis.
This paper examines how the rapid advancement of AI, particularly with foundation models and unstructured data, introduces new challenges in latency, scalability, and interpretability for human-data interaction, arguing for a paradigm shift that redefines human-machine roles and integrates cognitive and perceptual principles to build more effective, human-centered analytical systems.
This paper presents and experimentally demonstrates a purely photonic deep neuromorphic network that achieves 100% accuracy on a letter recognition task by utilizing a local optical feedback mechanism with non-volatile phase-change material synapses to enable online, unsupervised Hebbian learning without inefficient optical-electrical-optical conversions.
This paper presents a robust neuromorphic platform for machine learning that implements optical neural networks using only linear optical resources and coherent states, achieving necessary nonlinearity through phase-shift encoding to enable straightforward experimental in situ training and inference while demonstrating high resilience to photon losses.
This study employs a stochastic-process model to demonstrate that the optimal autocorrelation of time-series signals for solving multi-armed bandit problems depends on the reward environment, with negative autocorrelation being advantageous in reward-rich settings and positive autocorrelation in reward-poor ones, while performance remains independent of autocorrelation when the sum of winning probabilities equals one.
This paper investigates the adversarial robustness of partitioned quantum classifiers by demonstrating that perturbations targeting circuit partitioning techniques, such as wire cutting or teleportation, are equivalent to implementing adversarial gates within intermediate layers, a relationship analyzed through both theoretical and experimental perspectives.
This paper proposes a variability-driven systems engineering framework using Orthogonal Variability Modelling and Systems Modelling Language to systematically model, trace, and evolve Quantum Key Distribution network architectures, thereby addressing the challenges of integrating complex quantum devices into existing classical infrastructure to meet future security needs.
This study presents a novel computer vision framework that utilizes external observation techniques, including YOLO-based object detection and lane monitoring, to classify distracted and impaired driver behaviors in non-connected vehicles without relying on inter-vehicular communication.