Yanqiao Zhu
YOU?
Author Swipe
View article: MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science
MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science Open
Large Language Models (LLMs) have demonstrated remarkable abilities in scientific reasoning, yet their reasoning capabilities in materials science remain underexplored. To fill this gap, we introduce MatSciBench, a comprehensive college-le…
View article: Functional Characterisation of Alternative Oxidase Protein Isoproteins in <scp> <i>Arabidopsis thaliana</i> </scp>
Functional Characterisation of Alternative Oxidase Protein Isoproteins in <span> <i>Arabidopsis thaliana</i> </span> Open
The Alternative Oxidase (AOX) is encoded by a small gene family in plants. While being one of the most intensively studied plant mitochondrial proteins, it is primarily only one isoform, AOX1a, that is well studied. We investigated the sub…
View article: Abolishing <scp>ANAC017</scp>‐Mediated Mitochondria Retrograde Signalling Alleviates Ammonium Toxicity in <scp> <i>Arabidopsis thaliana</i></scp>
Abolishing <span>ANAC017</span>‐Mediated Mitochondria Retrograde Signalling Alleviates Ammonium Toxicity in <span> <i>Arabidopsis thaliana</i></span> Open
Ammonium (NH 4 + ), an important nitrogen source, often fails to stimulate plant growth as a sole nitrogen source, a phenomenon known as ammonium toxicity syndrome. NH 4 + is believed to disrupt cellular redox status by increasing chloropl…
View article: Comparative Analysis of Deep Learning Strategies for Hypertensive Retinopathy Detection from Fundus Images: From Scratch and Pre-trained Models
Comparative Analysis of Deep Learning Strategies for Hypertensive Retinopathy Detection from Fundus Images: From Scratch and Pre-trained Models Open
This paper presents a comparative analysis of deep learning strategies for detecting hypertensive retinopathy from fundus images, a central task in the HRDC challenge~\cite{qian2025hrdc}. We investigate three distinct approaches: a custom …
View article: MatLLMSearch: Crystal Structure Discovery with Evolution-Guided Large Language Models
MatLLMSearch: Crystal Structure Discovery with Evolution-Guided Large Language Models Open
Crystal structure generation is fundamental to materials science, enabling the discovery of novel materials with desired properties. While existing approaches leverage Large Language Models (LLMs) through extensive fine-tuning on materials…
View article: SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training
SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training Open
View article: SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training
SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training Open
Recent advancements highlight the potential of end-to-end real-time spoken dialogue systems, showcasing their low latency and high quality. In this paper, we introduce SLAM-Omni, a timbre-controllable, end-to-end voice interaction system w…
View article: Overexpression of the transcription factor ANAC017 results in a genomes uncoupled phenotype under lincomycin
Overexpression of the transcription factor ANAC017 results in a genomes uncoupled phenotype under lincomycin Open
SUMMARY Over‐expression (OE) lines for the ER‐tethered NAC transcription factor ANAC017 displayed de‐repression of gun marker genes when grown on lincomycin (lin). RNA‐seq revealed that ANAC017OE2 plants constitutively expressed greater th…
View article: Bi-Level Graph Structure Learning for Next POI Recommendation
Bi-Level Graph Structure Learning for Next POI Recommendation Open
Next point-of-interest (POI) recommendation aims to predict a user's next\ndestination based on sequential check-in history and a set of POI candidates.\nGraph neural networks (GNNs) have demonstrated a remarkable capability in this\nendea…
View article: BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers
BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers Open
Developing effective biomedical retrieval models is important for excelling at knowledge-intensive biomedical tasks but still challenging due to the deficiency of sufficient publicly annotated biomedical data and computational resources. W…
View article: An Evaluation of Large Language Models in Bioinformatics Research
An Evaluation of Large Language Models in Bioinformatics Research Open
Large language models (LLMs) such as ChatGPT have gained considerable interest across diverse research communities. Their notable ability for text completion and generation has inaugurated a novel paradigm for language-interfaced problem s…
View article: AKE-GNN: Effective Graph Learning with Adaptive Knowledge Exchange
AKE-GNN: Effective Graph Learning with Adaptive Knowledge Exchange Open
Graph Neural Networks (GNNs) have already been widely used in various graph mining tasks. However, recent works reveal that the learned weights (channels) in well-trained GNNs are highly redundant, which inevitably limits the performance o…
View article: GSLB: The Graph Structure Learning Benchmark
GSLB: The Graph Structure Learning Benchmark Open
Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of…
View article: Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks
Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks Open
Molecular Representation Learning (MRL) has proven impactful in numerous biochemical applications such as drug discovery and enzyme design. While Graph Neural Networks (GNNs) are effective at learning molecular representations from a 2D mo…
View article: Uncovering Neural Scaling Laws in Molecular Representation Learning
Uncovering Neural Scaling Laws in Molecular Representation Learning Open
Molecular Representation Learning (MRL) has emerged as a powerful tool for drug and materials discovery in a variety of tasks such as virtual screening and inverse design. While there has been a surge of interest in advancing model-centric…
View article: A Systematic Survey of Chemical Pre-trained Models
A Systematic Survey of Chemical Pre-trained Models Open
Deep learning has achieved remarkable success in learning representations for molecules, which is crucial for various biochemical applications, ranging from property prediction to drug design. However, training Deep Neural Networks (DNNs) …
View article: SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models
SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models Open
Most of the existing Large Language Model (LLM) benchmarks on scientific problem reasoning focus on problems grounded in high-school subjects and are confined to elementary algebraic operations. To systematically examine the reasoning capa…
View article: Unsupervised Graph Representation Learning with Cluster-aware Self-training and Refining
Unsupervised Graph Representation Learning with Cluster-aware Self-training and Refining Open
Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features. Previous Graph Neural Networks (GNN) require a large …
View article: Neighborhood-Regularized Self-Training for Learning with Few Labels
Neighborhood-Regularized Self-Training for Learning with Few Labels Open
Training deep neural networks (DNNs) with limited supervision has been a popular research topic as it can significantly alleviate the annotation burden. Self-training has been successfully applied in semi-supervised learning tasks, but one…
View article: M$^2$Hub: Unlocking the Potential of Machine Learning for Materials Discovery
M$^2$Hub: Unlocking the Potential of Machine Learning for Materials Discovery Open
We introduce M$^2$Hub, a toolkit for advancing machine learning in materials discovery. Machine learning has achieved remarkable progress in modeling molecular structures, especially biomolecules for drug discovery. However, the developmen…
View article: Code Recommendation for Open Source Software Developers
Code Recommendation for Open Source Software Developers Open
Open Source Software (OSS) is forming the spines of technology infrastructures, attracting millions of talents to contribute. Notably, it is challenging and critical to consider both the developers' interests and the semantic features of t…
View article: Deep Dag Learning of Effective Brain Connectivity for FMRI Analysis
Deep Dag Learning of Effective Brain Connectivity for FMRI Analysis Open
Functional magnetic resonance imaging (fMRI) has become one of the most common imaging modalities for brain function analysis. Recently, graph neural networks (GNN) have been adopted for fMRI analysis with superior performance. Unfortunate…
View article: Neighborhood-Regularized Self-Training for Learning with Few Labels
Neighborhood-Regularized Self-Training for Learning with Few Labels Open
Training deep neural networks (DNNs) with limited supervision has been a popular research topic as it can significantly alleviate the annotation burden. Self-training has been successfully applied in semi-supervised learning tasks, but one…
View article: A Survey on Pretrained Language Models for Neural Code Intelligence
A Survey on Pretrained Language Models for Neural Code Intelligence Open
As the complexity of modern software continues to escalate, software engineering has become an increasingly daunting and error-prone endeavor. In recent years, the field of Neural Code Intelligence (NCI) has emerged as a promising solution…
View article: Coordinated regulation of the mitochondrial retrograde response by circadian clock regulators and ANAC017
Coordinated regulation of the mitochondrial retrograde response by circadian clock regulators and ANAC017 Open
View article: BrainGB: A Benchmark for Brain Network Analysis With Graph Neural Networks
BrainGB: A Benchmark for Brain Network Analysis With Graph Neural Networks Open
Mapping the connectome of the human brain using structural or functional connectivity has become one of the most pervasive paradigms for neuroimaging analysis. Recently, Graph Neural Networks (GNNs) motivated from geometric deep learning h…
View article: Learning Task-Aware Effective Brain Connectivity for fMRI Analysis with Graph Neural Networks
Learning Task-Aware Effective Brain Connectivity for fMRI Analysis with Graph Neural Networks Open
Functional magnetic resonance imaging (fMRI) has become one of the most common imaging modalities for brain function analysis. Recently, graph neural networks (GNN) have been adopted for fMRI analysis with superior performance. Unfortunate…
View article: A Systematic Survey of Chemical Pre-trained Models
A Systematic Survey of Chemical Pre-trained Models Open
Deep learning has achieved remarkable success in learning representations for molecules, which is crucial for various biochemical applications, ranging from property prediction to drug design. However, training Deep Neural Networks (DNNs) …
View article: Deep Contrastive Multiview Network Embedding
Deep Contrastive Multiview Network Embedding Open
Multiview network embedding aims at projecting nodes in the network to\nlow-dimensional vectors, while preserving their multiple relations and\nattribute information. Contrastive learning approaches have shown promising\nperformance in thi…
View article: Code Recommendation for Open Source Software Developers
Code Recommendation for Open Source Software Developers Open
Open Source Software (OSS) is forming the spines of technology infrastructures, attracting millions of talents to contribute. Notably, it is challenging and critical to consider both the developers' interests and the semantic features of t…