arXiv subjects

Mingcheng Luo

Publications and source records attributed to Mingcheng Luo.

4 recordsLinked to original sources

arXiv2026

Meta-Optics-Based Diffractive Learning Machine for Angle-Multiplexed Multi-Task Processing

All-optical diffractive neural networks (DNNs) offer low latency, low energy consumption, and massive parallelism. However, their scalability in terms of network scale and multi-task processing remains limited. Here, we experimentally demonstrate a large-scale metasurface-based diffractive learning machine for angle-multiplexed multi-task processing. Our system employs a metasurface-based reflection cavity to realize a five-layer DNN comprising 115 million fixed, untrained diffractive nodes within a compact volume of 216 mm^3. By integrating this large-scale, untrained DNN with a lightweight, trainable digital backend containing only 7,680 parameters, our system experimentally achieves an accuracy of 95.3% on the standard full-scale CIFAR-10 dataset, significantly outperforming previous optical neural networks and rivaling large-scale digital models. Using a novel incident-angle-multiplexing scheme, our system experimentally achieves parallel processing of 11 tasks with negligible performance degradation, representing the largest multi-task processing capacity reported to date. Our work provides a scalable and energy-efficient solution for high-performance edge computing.

physics.optics↗

arXiv2026

BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents

Mobile GUI agents are shifting from multi-module frameworks to native models trained end-to-end, yet industrial deployment faces three persistent gaps. Sandbox training produces a distribution mismatch with production environments; expensive real-device failures remain underutilized; and fixed benchmarks saturate, losing the power to guide iteration. We present BlueLM-GUI, a 35B-A3B mobile GUI agent built as a real-device-centric flywheel that closes these gaps through three principles. Every Sample Matters: a dual-track pipeline with Heterogeneous Triple-System Consensus evaluation and an Error Correction \& Derivation Module salvages every trajectory into usable supervision. Every Rollout Is Real: a three-stage recipe---continual pre-training, supervised fine-tuning, and agentic reinforcement learning on hundreds of real phones---grounds every rollout in real production environments, so the capability the model learns transfers directly to deployment. Every Query Evolves: a quota-driven benchmark methodology with three orthogonal axes enables precise attribution and allows the benchmark to be systematically upgraded as the model improves. BlueLM-GUI achieves 87.4 on MobileGUI-VBench, surpassing the best closed-source model by 5.1 points, and 84.9 on AndroidWorld, the best result among open-source models and competitive with closed-source models. These results demonstrate that grounding model training and iterative improvement in both real devices and the three Every principles yields strong, robust, and transferable mobile GUI capability.

cs.AI↗

arXiv2025

Large-scale artificial intelligence with 41 million nanophotonic neurons on a metasurface

Conventional integrated circuits (ICs) struggle to meet the escalating demands of artificial intelligence (AI). This has sparked a renewed interest in an unconventional computing paradigm: neuromorphic (brain-inspired) computing. However, current neuromorphic systems face significant challenges in delivering a large number of parameters (i.e., weights) required for large-scale AI models. As a result, most neuromorphic hardware is limited to basic benchmark demonstrations, hindering its application to real-world AI challenges. Here, we present a large-scale optical neural network (ONN) for machine learning acceleration, featuring over 41 million photonic neurons. This system not only surpasses digital electronics in speed and energy efficiency but more importantly, closes the performance gap with large-scale AI models. Our ONN leverages an innovative optical metasurface device featuring numerous spatial modes. This device integrates over 41 million meta-atoms on a 10 mm$^2$ metasurface chip, enabling the processing of tens of millions of weights in a single operation. For the first time, we demonstrate that an ONN, utilizing a single-layer metasurface, can match the performance of deep and large-scale deep learning models, such as ResNet and Vision Transformer, across various benchmark tasks. Additionally, we show that our system can deliver high-performance solutions to real-world AI challenges through its unprecedented scale, such as accelerating the analysis of multi-gigapixel whole slide images (WSIs) for cancer detection by processing the million-pixel sub-image in a single shot. Our system reduces computing time and energy consumption by over 1,000 times compared to state-of-the-art graphic processing units (GPUs). This work presents a large-scale, low-power, and high-performance neuromorphic computing system, paving the way for future disruptive AI technologies.

physics.optics↗

arXiv2024

Control-free and efficient integrated photonic neural networks via hardware-aware training and pruning

Integrated photonic neural networks (PNNs) are at the forefront of AI computing, leveraging on light's unique properties, such as large bandwidth, low latency, and potentially low power consumption. Nevertheless, the integrated optical components within PNNs are inherently sensitive to external disturbances and thermal interference, which can detrimentally affect computing accuracy and reliability. Current solutions often use complicated control methods, resulting in high hardware complexity impractical for large-scale PNNs. In response, we propose a novel hardware-aware training and pruning approach. The core idea is to train the parameters of a physical neural network towards its noise-robust and energy-efficient region. This innovation enables control-free and energy-efficient photonic computing. Our method is validated across diverse integrated PNN architectures. Through experimental validation, our approach significantly enhances the computing precision of MRR-based PNN, achieving a notable 4-bit improvement without the need for complex device control mechanisms or energy-intensive temperature stabilization circuits. Specifically, it improves the accuracy of experimental handwritten digit classification from 67.0% to 95.0%, nearing theoretical limits and achieved without a thermoelectric controller. Additionally, this approach reduces the energy by tenfold. We further extend the validation to various architectures, such as PCM-based PNN, demonstrating the broad applicability of our approach across different platforms. This advancement represents a significant step towards the practical, energy-efficient, and noise-resilient implementation of large-scale integrated PNNs.

physics.optics↗