arXiv subjects

Zhongyue Zhang

Publications and source records attributed to Zhongyue Zhang.

18 recordsLinked to original sources

arXiv2026

Does Learning Protein Folding Generalize to Broader Reasoning?

Large language models rely heavily on human text, which often conveys surface answers rather than the spatial and structural logic behind them. Protein folding is a natural testbed, because one solved structure yields thousands of exactly checkable spatial and topological statements. We ask: can learning to fold proteins teach general models reusable reasoning capabilities? To answer this, we build FoldingCorpus, a protein-derived question-answer dataset, and Fold2Reason, a recipe that post-trains on it through two complementary signals: discrete structural answers predicted via the model's native language head, and continuous 3D geometry decoded from the same shared representations. On FoldBench, Fold2Reason achieves structure prediction scores 2.7 to 3.5 times those of Qwen3.5-9B. Beyond protein structure prediction, it improves performance on all 10 benchmarks spanning spatial, graph, scientific, and general reasoning, raising macro-average accuracy from 45.09% to 48.33% (+3.23 pp), with positive gains on all 10 benchmarks, while matched controls built from random, synthetic, and shuffled structure yield substantially smaller or negative gains. Our work shows that non-linguistic, structure-dense scientific data can systematically improve broad reasoning in language models, making a solved scientific problem a practical source of post-training supervision.

cs.LG↗

arXiv2026

Recovery of 21 cm BAO: a configuration-space correlation function analysis

Intensity mapping (IM) represents an innovative and potent probe to cosmology. One of its prime applications is to measure the Baryonic Acoustic Oscillations (BAO) in the late universe. We study the BAO measurement by IM in configuration space using simulations, focusing on the impact of the telescope beam and foreground removal effects, which are modeled by a Gaussian beam and radial power suppression, respectively. Three types of correlation functions are applied to measure BAO, including the radial correlation function, multipole correlation function, and wedge correlation function. We check our pipeline against a set of IM mock catalogs, finding good agreement with the numerical results. We use the mock catalogs to look for the parameter choices that optimize the BAO constraint for the correlation function estimators. With the optimal settings, our pipeline is utilized to forecast the BAO constraint for the 21 cm IM experiments: BINGO, MeerKAT, and SKA-mid. Despite our simple beam and foreground removal effect treatments, our analyses could offer a useful guide to strengthen the constraining power of these experiments. We find that for the low-redshift experiments BINGO and MeerKAT, the wedge correlation function achieves the tightest constraint for both the transverse and radial BAO. For SKA-mid, the radial correlation function and multipole correlation function deliver the tightest constraint for the radial and transverse BAO, respectively.

astro-ph.CO↗

arXiv2026

Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design

Antibodies are essential proteins that play a central role in immune recognition by binding specific antigen molecules. Although recent protein language models have enabled progress in single-chain protein modeling and generation, they often fall short in antigen-specific antibody design, where effective modeling requires explicit pairing between antibody and antigen, particularly at the epitope level. To address these limitations, we introduce AAMFM, an Antigen-specific Antibody Multimodal Foundation Model that learns unified representations of antibody sequences and structures conditioned on antigen context. AAMFM incorporates rich antigen information including geometric interfaces and epitope annotations via a cross-modal adapter, enabling joint modeling of antibody-antigen interactions in a shared latent space. To further guide the model toward functional relevance, we fine-tune AAMFM using Calibrated Direct Preference Optimization (Cal-DPO), leveraging preference signals extracted from a strong structural prior to align learning with binding-specific objectives. Extensive experiments demonstrate that AAMFM achieves state-of-the-art performance in functional antibody design, revealing its potential for antigen-specific antibody engineering. Our code is available at https://github.com/XL-S224/AAMFM.

q-bio.BM↗

arXiv2026

AdaKernel: Learning Adaptive Kernel Parameters for Spatiotemporal Graph Neural Networks

Modeling spatial dependencies is central to spatiotemporal data analysis using Graph Neural Networks (GNNs). Traditional methods rely on distance-based kernels with predefined parameters, which restricts model capacity. Although generic adaptive mechanisms (e.g., Graph Attention Networks) offer flexibility, they often fail to capture the underlying geometric structure, performing worse than distance-based models in data-sparse scenarios. Addressing this, we revisit the kernel parameterization problem and theoretically prove that misspecified kernel parameters introduce unavoidable approximation errors in GNNs. To overcome this, we propose AdaKernel, a simple yet effective approach that learns adaptive kernel parameters within the neural network. Unlike methods that learn graph structures from scratch, AdaKernel adopts a structure-preserving strategy that optimizes the scale of physical interactions rather than discarding them. Extensive experiments on Kriging, Imputation, and Forecasting demonstrate that AdaKernel consistently improves various GNN architectures and outperforms model-agnostic adaptive baselines, validating that accurately learned kernel parameters are superior to both fixed priors and fully latent graph structures.

cs.LG↗

arXiv2025

RiboFlow: Conditional De Novo RNA Co-Design via Synergistic Flow Matching

Ribonucleic acid (RNA) binds to molecules to achieve specific biological functions. While generative models are advancing biomolecule design, existing methods for designing RNA that target specific ligands face limitations in capturing RNA's conformational flexibility, ensuring structural validity, and overcoming data scarcity. To address these challenges, we introduce RiboFlow, a synergistic flow matching model to co-design RNA structures and sequences based on target molecules. By integrating RNA backbone frames, torsion angles, and sequence features in an unified architecture, RiboFlow explicitly models RNA's dynamic conformations while enforcing sequence-structure consistency to improve validity. Additionally, we curate RiboBind, a large-scale dataset of RNA-molecule interactions, to resolve the scarcity of high-quality structural data. Extensive experiments reveal that RiboFlow not only outperforms state-of-the-art RNA design methods by a large margin but also showcases controllable capabilities for achieving high binding affinity to target ligands. Our work bridges critical gaps in controllable RNA design, offering a framework for structure-aware, data-efficient generation.

q-bio.BM↗

arXiv2025

Fitness aligned structural modeling enables scalable virtual screening with AuroBind

Most human proteins remain undrugged, over 96% of human proteins remain unexploited by approved therapeutics. While structure-based virtual screening promises to expand the druggable proteome, existing methods lack atomic-level precision and fail to predict binding fitness, limiting translational impact. We present AuroBind, a scalable virtual screening framework that fine-tunes a custom atomic-level structural model on million-scale chemogenomic data. AuroBind integrates direct preference optimization, self-distillation from high-confidence complexes, and a teacher-student acceleration strategy to jointly predict ligand-bound structures and binding fitness. The proposed models outperform state-of-the-art models on structural and functional benchmarks while enabling 100,000-fold faster screening across ultra-large compound libraries. In a prospective screen across ten disease-relevant targets, AuroBind achieved experimental hit rates of 7-69%, with top compounds reaching sub-nanomolar to picomolar potency. For the orphan GPCRs GPR151 and GPR160, AuroBind identified both agonists and antagonists with success rates of 16-30%, and functional assays confirmed GPR160 modulation in liver and prostate cancer models. AuroBind offers a generalizable framework for structure-function learning and high-throughput molecular screening, bridging the gap between structure prediction and therapeutic discovery.

cs.LG↗

arXiv2025

RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World

Existing robot policies predominantly adopt the task-centric approach, requiring end-to-end task data collection. This results in limited generalization to new tasks and difficulties in pinpointing errors within long-horizon, multi-stage tasks. To address this, we propose RoboMatrix, a skill-centric hierarchical framework designed for scalable robot task planning and execution in open-world environments. RoboMatrix extracts general meta-skills from diverse complex tasks, enabling the completion of unseen tasks through skill composition. Its architecture consists of a high-level scheduling layer that utilizes large language models (LLMs) for task decomposition, an intermediate skill layer housing meta-skill models, and a low-level hardware layer for robot control. A key innovation of our work is the introduction of the first unified vision-language-action (VLA) model capable of seamlessly integrating both movement and manipulation within one model. This is achieved by combining vision and language prompts to generate discrete actions. Experimental results demonstrate that RoboMatrix achieves a 50% higher success rate than task-centric baselines when applied to unseen objects, scenes, and tasks. To advance open-world robotics research, we will open-source code, hardware designs, model weights, and datasets at https://github.com/WayneMao/RoboMatrix.

cs.RO↗

arXiv2025

An Energy-Adaptive Elastic Equivariant Transformer Framework for Protein Structure Representation

Structure-informed protein representation learning is essential for effective protein function annotation and \textit{de novo} design. However, the presence of inherent noise in both crystal and AlphaFold-predicted structures poses significant challenges for existing methods in learning robust protein representations. To address these issues, we propose a novel equivariant Transformer-State Space Model(SSM) hybrid framework, termed $E^3$former, designed for efficient protein representation. Our approach uses energy function-based receptive fields to construct proximity graphs and incorporates an equivariant high-tensor-elastic selective SSM within the transformer architecture. These components enable the model to adapt to complex atom interactions and extract geometric features with higher signal-to-noise ratios. Empirical results demonstrate that our model outperforms existing methods in structure-intensive tasks, such as inverse folding and binding site prediction, particularly when using predicted structures, owing to its enhanced tolerance to data deviation and noise. Our approach offers a novel perspective for conducting biological function research and drug discovery using noisy protein structure data.

q-bio.BM↗

arXiv2024

Understanding and Co-designing Photo-based Reminiscence with Older Adults

Reminiscence, the act of revisiting past memories, is crucial for self-reflection and social interaction, significantly enhancing psychological well-being, life satisfaction, and self-identity among older adults. In HCI and CSCW, there is growing interest in leveraging technology to support reminiscence for older adults. However, understanding how older adults actively use technologies for realistic and practical reminiscence in their daily lives remains limited. This paper addresses this gap by providing an in-depth, empirical understanding of technology-mediated, photo-based reminiscence among older adults. Through a two-part study involving 20 older adults, we conducted semi-structured interviews and co-design sessions to explore their use and vision of digital technologies for photo-based reminiscence activities. Based on these insights, we propose design implications to make future reminiscence technologies more accessible and empowering for older adults.

cs.HC↗

arXiv2022

WISPLC: Search for Dark Matter with LC Circuit

The focus on dark matter search has expanded to include low-mass particles such as axions or axion-like particles, and novel theoretical schemes extending the phenomenological landscape, within QCD and beyond, also garnered additional interest in recent decades. Assuming dark matter is composed of axions, in presence of a solenoidal magnetic field, they induce a displacement current that gives rise to a toroidal magnetic field. The Weakly Interacting Slender Particle detection with LC circuit (WISPLC) is a precision direct detection experiment that will search for light dark matter candidates such as axion-like particles in parts of the parameter space previously unexplored. We present two detection schemes of the signal in a pickup loop capturing the flux of this toroidal magnetic field. WISPLC operates in a broadband and a resonant scheme where a LC circuit is used to enhance the signal with an expected Q factor $\sim 10^4$. Taking into account the irreducible flux noise of the detector, we estimate the sensitivity of the experiment in the axion mass range between $10^{-11}$ eV and $10^{-6}$ eV to reach a detectable axion-photon coupling of $g_{aγγ}\approx 10^{-15}~\mathrm{GeV}^{-1}$, making it possible to probe mass ranges corresponding to ultralight axions motivated by string theory. The WISPLC experiment is fully funded and currently in the construction phase.

hep-ex↗

arXiv2020

ResNeSt: Split-Attention Networks

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our design results in a simple and unified computation block, which can be parameterized using only a few variables. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification. In addition, ResNeSt has achieved superior transfer learning results on several public benchmarks serving as the backbone, and has been adopted by the winning entries of COCO-LVIS challenge. The source code for complete system and pretrained models are publicly available.

cs.CV↗

arXiv2020

Improving Semantic Segmentation via Self-Training

Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we can obtain state-of-the-art results using a semi-supervised approach, specifically a self-training paradigm. We first train a teacher model on labeled data, and then generate pseudo labels on a large set of unlabeled data. Our robust training framework can digest human-annotated and pseudo labels jointly and achieve top performances on Cityscapes, CamVid and KITTI datasets while requiring significantly less supervision. We also demonstrate the effectiveness of self-training on a challenging cross-domain generalization task, outperforming conventional finetuning method by a large margin. Lastly, to alleviate the computational burden caused by the large amount of pseudo labels, we propose a fast training schedule to accelerate the training of segmentation models by up to 2x without performance degradation.

cs.CV↗

arXiv2020

GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing

We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating). These toolkits provide state-of-the-art pre-trained models, training scripts, and training logs, to facilitate rapid prototyping and promote reproducible research. We also provide modular APIs with flexible building blocks to enable efficient customization. Leveraging the MXNet ecosystem, the deep learning models in GluonCV and GluonNLP can be deployed onto a variety of platforms with different programming languages. The Apache 2.0 license has been adopted by GluonCV and GluonNLP to allow for software distribution, modification, and usage.

cs.LG↗

arXiv2019

Predicting Retrosynthetic Reaction using Self-Corrected Transformer Neural Networks

Synthesis planning is the process of recursively decomposing target molecules into available precursors. Computer-aided retrosynthesis can potentially assist chemists in designing synthetic routes, but at present it is cumbersome and provides results of dissatisfactory quality. In this study, we develop a template-free self-corrected retrosynthesis predictor (SCROP) to perform a retrosynthesis prediction task trained by using the Transformer neural network architecture. In the method, the retrosynthesis planning is converted as a machine translation problem between molecular linear notations of reactants and the products. Coupled with a neural network-based syntax corrector, our method achieves an accuracy of 59.0% on a standard benchmark dataset, which increases >21% over other deep learning methods, and >6% over template-based methods. More importantly, our method shows an accuracy 1.7 times higher than other state-of-the-art methods for compounds not appearing in the training set.

physics.chem-ph↗

arXiv2019

Bag of Freebies for Training Object Detection Neural Networks

Training heuristics greatly improve various image classification model accuracies~\cite{he2018bag}. Object detection models, however, have more complex neural network structures and optimization targets. The training strategies and pipelines dramatically vary among different models. In this works, we explore training tweaks that apply to various models including Faster R-CNN and YOLOv3. These tweaks do not change the model architectures, therefore, the inference costs remain the same. Our empirical results demonstrate that, however, these freebies can improve up to 5% absolute precision compared to state-of-the-art baselines.

cs.CV↗

arXiv2018

Bag of Tricks for Image Classification with Convolutional Neural Networks

Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods. In the literature, however, most refinements are either briefly mentioned as implementation details or only visible in source code. In this paper, we will examine a collection of such refinements and empirically evaluate their impact on the final model accuracy through ablation study. We will show that, by combining these refinements together, we are able to improve various CNN models significantly. For example, we raise ResNet-50's top-1 validation accuracy from 75.3% to 79.29% on ImageNet. We will also demonstrate that improvement on image classification accuracy leads to better transfer learning performance in other application domains such as object detection and semantic segmentation.

cs.CV↗

arXiv2018

Context Encoding for Semantic Segmentation

Recent work has made significant progress in improving spatial resolution for pixelwise labeling with Fully Convolutional Network (FCN) framework by employing Dilated/Atrous convolution, utilizing multi-scale features and refining boundaries. In this paper, we explore the impact of global contextual information in semantic segmentation by introducing the Context Encoding Module, which captures the semantic context of scenes and selectively highlights class-dependent featuremaps. The proposed Context Encoding Module significantly improves semantic segmentation results with only marginal extra computation cost over FCN. Our approach has achieved new state-of-the-art results 51.7% mIoU on PASCAL-Context, 85.9% mIoU on PASCAL VOC 2012. Our single model achieves a final score of 0.5567 on ADE20K test set, which surpass the winning entry of COCO-Place Challenge in 2017. In addition, we also explore how the Context Encoding Module can improve the feature representation of relatively shallow networks for the image classification on CIFAR-10 dataset. Our 14 layer network has achieved an error rate of 3.45%, which is comparable with state-of-the-art approaches with over 10 times more layers. The source code for the complete system are publicly available.

cs.CV↗

arXiv2016

megaman: Manifold Learning with Millions of points

Manifold Learning is a class of algorithms seeking a low-dimensional non-linear representation of high-dimensional data. Thus manifold learning algorithms are, at least in theory, most applicable to high-dimensional data and sample sizes to enable accurate estimation of the manifold. Despite this, most existing manifold learning implementations are not particularly scalable. Here we present a Python package that implements a variety of manifold learning algorithms in a modular and scalable fashion, using fast approximate neighbors searches and fast sparse eigendecompositions. The package incorporates theoretical advances in manifold learning, such as the unbiased Laplacian estimator and the estimation of the embedding distortion by the Riemannian metric method. In benchmarks, even on a single-core desktop computer, our code embeds millions of data points in minutes, and takes just 200 minutes to embed the main sample of galaxy spectra from the Sloan Digital Sky Survey --- consisting of 0.6 million samples in 3750-dimensions --- a task which has not previously been possible.

cs.LG↗