arXiv subjects

Xianchao Guan

Publications and source records attributed to Xianchao Guan.

7 recordsLinked to original sources

arXiv2026

A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design

The rapid expansion of large-scale AI models has led to significant performance breakthroughs across diverse domains, yet it has also raised critical concerns regarding computational costs, energy consumption, and environmental sustainability. This survey provides a comprehensive overview of the green development of large models, emphasizing resource-efficient architectures and full-stack hardware-software co-design. We systematically review recent advances in efficient model construction, including attention operator optimization, linear-complexity architectures, and model sparsification and merging, as well as training and deployment strategies such as data-efficient learning, parameter-efficient fine-tuning, and computational compression. Beyond algorithmic improvements, we explore energy-efficient AI hardware, including mainstream AI chips, memory optimization, cross-platform deployment, and sustainable infrastructure. Furthermore, we examine how large models are being applied to sustainability-critical domains such as DeepSeek, remote sensing interpretation, national-scale infrastructure, and global initiatives. Finally, we discuss key challenges and future directions, highlighting the need for continual learning paradigms, memory-centric hardware, and standardized evaluation protocols. This survey aims to offer a holistic roadmap toward sustainable, scalable, and socially responsible development of large models. Paper homepage: https://cje.ejournal.org.cn/article/doi/10.23919/cje.2025.00.438

cs.LG↗

arXiv2026

AGFT: Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Models

Pre-trained vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial perturbations. Existing classification-guided adversarial fine-tuning methods often disrupt pre-trained cross-modal alignment, weakening visual-textual correspondence and degrading zero-shot performance. In this paper, we propose an Alignment-Guided Fine-Tuning (AGFT) framework that enhances zero-shot adversarial robustness while preserving the cross-modal semantic structure. Unlike label-based methods that rely on hard labels and fail to maintain the relative relationships between image and text, AGFT leverages the probabilistic predictions of the original model for text-guided adversarial training, which aligns adversarial visual features with textual embeddings via soft alignment distributions, improving zero-shot adversarial robustness. To address structural discrepancies introduced by fine-tuning, we introduce a distribution consistency calibration mechanism that adjusts the robust model output to match a temperature-scaled version of the pre-trained model predictions. Extensive experiments across multiple zero-shot benchmarks demonstrate that AGFT outperforms state-of-the-art methods while significantly improving zero-shot adversarial robustness.

cs.CV↗

arXiv2025

A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis

The development of clinical-grade artificial intelligence in pathology is limited by the scarcity of diverse, high-quality annotated datasets. Generative models offer a potential solution but suffer from semantic instability and morphological hallucinations that compromise diagnostic reliability. To address this challenge, we introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS), the first generative foundation model for pathology-specific text-to-image synthesis. By leveraging a dual-stage training strategy on approximately 2.8 million image-caption pairs, CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy. This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations. Furthermore, CRAFTS-augmented datasets enhance the performance across various clinical tasks, including classification, cross-modal retrieval, self-supervised learning, and visual question answering. In addition, coupling CRAFTS with ControlNet enables precise control over tissue architecture from inputs such as nuclear segmentation masks and fluorescence images. By overcoming the critical barriers of data scarcity and privacy concerns, CRAFTS provides a limitless source of diverse, annotated histology data, effectively unlocking the creation of robust diagnostic tools for rare and complex cancer phenotypes.

cs.CV↗

arXiv2025

Category Prompt Mamba Network for Nuclei Segmentation and Classification

Nuclei segmentation and classification provide an essential basis for tumor immune microenvironment analysis. The previous nuclei segmentation and classification models require splitting large images into smaller patches for training, leading to two significant issues. First, nuclei at the borders of adjacent patches often misalign during inference. Second, this patch-based approach significantly increases the model's training and inference time. Recently, Mamba has garnered attention for its ability to model large-scale images with linear time complexity and low memory consumption. It offers a promising solution for training nuclei segmentation and classification models on full-sized images. However, the Mamba orientation-based scanning method lacks account for category-specific features, resulting in sub-optimal performance in scenarios with imbalanced class distributions. To address these challenges, this paper introduces a novel scanning strategy based on category probability sorting, which independently ranks and scans features for each category according to confidence from high to low. This approach enhances the feature representation of uncertain samples and mitigates the issues caused by imbalanced distributions. Extensive experiments conducted on four public datasets demonstrate that our method outperforms state-of-the-art approaches, delivering superior performance in nuclei segmentation and classification tasks.

cs.CV↗

arXiv2023

Breast Cancer Immunohistochemical Image Generation: a Benchmark Dataset and Challenge Review

For invasive breast cancer, immunohistochemical (IHC) techniques are often used to detect the expression level of human epidermal growth factor receptor-2 (HER2) in breast tissue to formulate a precise treatment plan. From the perspective of saving manpower, material and time costs, directly generating IHC-stained images from Hematoxylin and Eosin (H&E) stained images is a valuable research direction. Therefore, we held the breast cancer immunohistochemical image generation challenge, aiming to explore novel ideas of deep learning technology in pathological image generation and promote research in this field. The challenge provided registered H&E and IHC-stained image pairs, and participants were required to use these images to train a model that can directly generate IHC-stained images from corresponding H&E-stained images. We selected and reviewed the five highest-ranking methods based on their PSNR and SSIM metrics, while also providing overviews of the corresponding pipelines and implementations. In this paper, we further analyze the current limitations in the field of breast cancer immunohistochemical image generation and forecast the future development of this field. We hope that the released dataset and the challenge will inspire more scholars to jointly study higher-quality IHC-stained image generation.

eess.IV↗

arXiv2020

Fiber-based narrowband bright squeezed light generation by double-pass parametric amplification

The squeezed states of light become more and more important in the fields of quantum enhanced precision measurement and quantum information. To get this vital continuous variable quantum resource, the generation of squeezed states of light becomes a key factor. In this paper, a compact telecom fiber-based bright squeezed light (BSL) generator is demonstrated. To our knowledge, this is the first time that BSL has been reported in a fiber-based system to date. To obtain the BSL, a double-pass parametric amplifier based on surface-coated lithium niobate waveguide is employed. When the 1550 nm seed laser of the parametric amplifier is blocked, a stable 1.85 dB squeezed vacuum is obtained. With injected seed power of 80 μW, an output power of 18 μW and a squeezing value of 1.04 dB are achieved of the BSL at 1550 nm. Due to the good mode matching in the fiber and the absence of the resonant cavity, this flexible and compact BSL generator has the potential to be useful in out-of-the-laboratory quantum technologies. Moreover, the BSL has a narrow spectral width of 30 kHz, which is inherited from a narrow-linewidth single-frequency seed laser. In addition to being free from the wavelength-dependent losses, the narrowband BSL is also beneficial to improve the signal-to-noise ratio of quantum-enhanced precision measurement.

quant-ph↗

arXiv2019

High-efficiency and high-power single-frequency fiber laser at 1.6 um based on cascaded energy-transfer pumping

In this paper, a technique combing cascaded energy-transfer pumping (CEP) method and master-oscillator power-amplifier (MOPA) configuration is proposed for power scaling of 1.6-um-band single-frequency fiber lasers (SFFLs), where the Er3+ ion has a limited gain. The CEP technique is fulfilled by coupling a primary signal light at 1.6 um and a C-band auxiliary laser. The numerical model of the fiber amplifier with the CEP technique reveals that the energy transfer process involves the pump competition and the in-band particle transition between the signal and auxiliary lights. Moreover, for the signal emission, the population density in the upper level is enhanced and the effective population inversion is achieved due to the CEP. A single-frequency MOPA laser at 1603 nm with an output power of 52.6 W is obtained experimentally. Besides, a slope efficiency of 30.4% is improved by more than 10% through the CEP technique. Both the output power and slope efficiency are by far the highest for 1.6-um-band SFFLs. Meanwhile, a laser linewidth of 5.2 kHz and a polarization-extinction ratio of ~18 dB are obtained at the maximum output power. The proposed technique provides an optional method of increasing the slope efficiency and power scaling for fiber lasers operating at L-band.

physics.optics↗