Yunfan Li

Targeting mitochondrial α-ketoglutarate sequestration disables dual oncogenic drivers and metabolic adaptability in pancreatic ductal adenocarcinoma

Yeting Xu, Hongjiang Guo, Shengxi Li, Yucheng Wang et autres

Pancreatic ductal adenocarcinoma (PDAC) exhibits hyperactive mitochondrial metabolism, yet how this rewiring spatially restricts the availability of metabolites for oncogenic signaling and drives systemic metabolic dysregulation in PDAC remains unknown. Here, we identify enhanced mitochondrial α-ketoglutarate (α-KG) sequestration as a key metabolic …

cn (code pays fourni par la source)

Risk-Aware Medical Question Answering as a Reliability-Critical Decision Process

Yi Luo, Yunfan Li

Deploying large language models for medical question answering requires not only accurate responses but also explicit risk control under uncertainty. Although retrieval-augmented generation reduces hallucinations with external evidence, medical RAG often assumes that retrieved evidence is clinically valid and sufficient—an assumption frequently …

cn (code pays fourni par la source)

Deep Reinforcement Learning-Based Beamforming Design for Multi-Irs Systems

Junlong Wang, Zhenni Pan, Yunfan Li, Shigeru Shimamoto et autres

Intelligent Reflecting Surfaces (IRS) enable the smart configuration of wireless environments via software control of a larger number of programmable passive reflective elements. A multi-IRS system has been shown to exhibit superior performance when compared to a single-IRS system. However, challenges such …

jp, no (code pays fourni par la source)

Probabilistic Multimodal Learning with von Mises-Fisher Distributions

Peng Hu, Yang Qin, Yuanbiao Gou, Yunfan Li et autres

Multimodal learning is pivotal for the advancement of artificial intelligence, enabling machines to integrate complementary information from diverse data sources for holistic perception and understanding. Despite significant progress, existing methods struggle with challenges such as noisy inputs, noisy correspondence, and the inherent …

cn, at (code pays fourni par la source)

A bibliometric study of the top 100 most-cited papers in ureteral stricture reconstruction

Jingke He, J. Li, S. S. Su, Yu Luo et autres

Background: Ureteral stricture is caused by iatrogenic and non-iatrogenic factors. The treatment of ureteral stricture usually involves ureteral reconstruction. This study aimed to identify and analyze the top 100 most cited (T100) papers in ureteral stricture reconstruction, a field lacking prior bibliometric …

cn (code pays fourni par la source)

Prediction of yield and quality in medicinal plant Ligusticum chuanxiong Hort. using uncrewed aerial vehicle multispectral measurement

Yunfan Li, Wu Chen, Hongmei Jia, Xi Chen et autres

Accurate predicting the yield and quality of medicinal materials before harvest can effectively guide post-harvest process, including processing and storage, thereby ensuring the final quality of medicinal materials. Currently, traditional experimental methods for yield and quality estimation are inadequate to offer reliable …

cn (code pays fourni par la source)

Frontiers and hotspots of 3D technology in prostatectomy from 1999 to 2024: a bibliometric analysis and visualization

Jingke He, Chengcheng Wei, S. S. Su, Yu Luo et autres

Background: Prostate cancer is a major global health issue. Radical prostatectomy is an effective treatment for prostate cancer. The integration of three-dimensional (3D) technology in prostatectomy offers numerous benefits. We intended to perform a bibliometric analysis of the role of 3D technology …

cn (code pays fourni par la source)

MetaQ: fast, scalable and accurate metacell inference via single-cell quantization

Yunfan Li, Hancong Li, Yijie Lin, Dan Zhang et autres

To overcome the computational barriers of analyzing large-scale single-cell sequencing data, we introduce MetaQ, a metacell algorithm that scales to arbitrarily large datasets with linear runtime and constant memory usage. Inspired by cellular development, MetaQ conceptualizes each metacell as a collective ancestor …

cn, us (code pays fourni par la source)

DiFiC: Your Diffusion Model Holds the Secret to Fine-Grained Clustering

Ruohong Yang, Peng Hu, Xi Peng, Yunfan Li

Fine-grained clustering is a practical yet challenging task, whose essence lies in capturing the subtle differences between instances of different classes. Such subtle differences can be easily disrupted by data augmentation or be overwhelmed by redundant information in data, leading to significant …

Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning

Yiran Wang, Chenshu Liu, Yunfan Li, Sanae Amani et autres

The exploration \& exploitation dilemma poses significant challenges in reinforcement learning (RL). Recently, curiosity-based exploration methods achieved great success in tackling hard-exploration problems. However, they necessitate extensive hyperparameter tuning on different environments, which heavily limits the applicability and accessibility of this line …

An Empirical Study of Parameter Efficient Fine-tuning on Vision-Language Pre-train Model

Yuxin Tian, Mouxing Yang, Yunfan Li, Dayiheng Liu et autres

Recent studies applied Parameter Efficient Fine-Tuning techniques (PEFTs) to efficiently narrow the performance gap between pre-training and downstream. There are two important factors for various PEFTs, namely, the accessible data size and fine-tunable parameter size. A natural expectation for PEFTs is that …

cn (code pays fourni par la source)

A Survey on Deep Clustering: From the Prior Perspective

Yiding Lu, Haobin Li, Yunfan Li, Yijie Lin et autres

Facilitated by the powerful feature extraction ability of neural networks, deep clustering has achieved great success in analyzing high-dimensional and complex real-world data. The performance of deep clustering methods is affected by various factors such as network structures and learning objectives. However, …