Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Guanbin Li has a total of 39 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning

    by Keyang Zhong, Kuo Wang, Peng Liu, Quanlong Zheng, Junlin Xie, Zhijia Liang, Yanhao Zhang, Guanbin Li

  • Open Access

    3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians

    by Zeming Wei, Junyi Lin, Yang Liu, Weixing Chen, Jingzhou Luo, Guanbin Li, Liang Lin


  • Open Access

    TreeReward: Improve Diffusion Model via Tree-Structured Feedback Learning

    by Jiacheng Zhang, Jie Wu, Huafeng Kuang, Haiming Zhang, Yuxi Ren, Weifeng Chen, Manlin Zhang, Xuefeng Xiao, Guanbin Li

    Recently, there has been significant progress in leveraging human feedback to enhance diffusion-based image generation, garnering considerable interest and attention. However, existing methods fail to achieve a fine-grained performance boost for the following challenges: i) insufficient amount of fine-grained feedback data; ii) lack of effective fine-grained feedback learning framework; To tackle these challenges, we present TreeReward to facilitate the fine-grained feedback optimization for diffusion models. Specifically, to address the limitation of the fine-grained feedback data, we first design a novel "AI + Expert" feedback data construction pipeline, yielding about 2.2M high-quality feedback dataset encompassing six fine-grained dimensions at a relatively low cost. Built upon this dataset, we introduce a tree-structure reward model to exploit the fine-grained feedback data efficiently and provide tailored optimization during feedback learning. We validate the feedback learning performance of our method across different fine-grained dimensions and various downstream tasks. Extensive experiments on both Stable Diffusion v1.5 (SD1.5) and Stable Diffusion XL (SDXL) demonstrate the effectiveness of our method in enhancing the general and fine-grained generation and downstream tasks generalization.


  • Open Access

    Multi-modal Denoising Diffusion Pre-training for Whole-Slide Image Classification

    by Wei Lou, Guanbin Li, Xiang Wan, Haofeng Li

    Whole-slide image (WSI) classification methods play a crucial role in tumor diagnosis. Most of them use hematoxylin and eosin (H&E) stained images, while Immunohistochemistry (IHC) staining provides molecular markers and protein expression information that highlights cancer regions. However, obtaining IHC-stained images requires higher costs in practice. In this work, we propose a multi-modal denoising diffusion pre-training framework that harnesses the advantages of IHC staining to learn visual representations. The framework is trained with the H&E-to-IHC re-staining task and IHC-stained image reconstruction task, which helps capture the structural similarity and staining difference between two image modalities. The trained model can then provide IHC-guided features, by taking only H&E-stained images as inputs. Besides, we build a new class-constraint constrastive loss to achieve the semantic consistency between dual-modal features from our pre-training framework. To integrate with WSI classifiers based on multi-instance learning, we further propose a bag feature augmentation strategy to extend bags with the features extracted by our pre-trained model. Experimental results on three datasets show that our pre-training framework effectively improves WSI classification and surpasses the state-of-the-art pre-training approaches. Code and model are released via https://github.com/lhaof/MDDP


  • Open Access

    GraphVAE: Unveiling Dynamic Stock Relationships with Variational Autoencoder-based Factor Modeling

    by Yulong Jia, Guanxing Li, Ganlong Zhao, Xiangru Lin, Guanbin Li

    Factor models, originating in finance for asset pricing, are fundamental tools in quantitative investment. Recently, there has been a trend towards adopting more flexible machine learning approaches instead of previous linear models. However, traditional factor models and recent deep learning approaches either overlook the relationships among stocks or rely on static, predefined ones, which hampers their representational power and hinders their ability to dynamically adapt to market changes. To overcome this limitation, we introduce a novel dynamic factor model named GraphVAE. This model leverages temporal adaptive dynamic stock relationship graphs, facilitating improved information transfer among stocks within the dynamic probabilistic factor model. Experimental results on three real stock market datasets demonstrate that our method outperforms various state-of-the-art approaches.


  • Open Access

    Clear Cell Tumor of the Lung Could Be Aggressive: a case report and review of the literature

    by Leilei Shen, Jixing Lin, Zhipeng Ren, Bailin Wang, You Liu, Jing Yuan, Lianbin Zhan

    Background: Clear cell tumors of the lung (CCTLs) are rare and mostly benign pulmonary neoplasms arising from perivascular epithelioid cells. Only approximately 100 cases have been reported, and half of them were in China. Limited details about CCTLs often cause diagnostic or therapeutic problems. Case presentation: We describe a case of a 28-year-old woman with multiple gradually replicating and enlarging nodules in the left lower lobe. The patient underwent fine-needle aspiration biopsy and was diagnosed with CCTL. A left lower lobectomy and mediastinal lymph node dissection were performed. The gradual changes in size (1.4 cm to 2.8 cm) and quantity (10 to 49) of the CCTLs in this case were the biggest differences from previously reported cases. Conclusions: CCTLs are very uncommon and mostly benign PEComatous tumors with no specific morphologic features. We present a case of CCTL with multiplicity and rapid growth, which may indicate its aggressive nature. The accumulation of similar cases will help clarify the exact nature and improve our understanding of the disease.