arXiv subjects

Yue Zhuo

Publications and source records attributed to Yue Zhuo.

11 recordsLinked to original sources

arXiv2026

Structural Graph Probing of Vision-Language Models

Vision-language models (VLMs) achieve strong multimodal performance, yet how computation is organized across populations of neurons remains poorly understood. In this work, we study VLMs through the lens of neural topology, representing each layer as a within-layer correlation graph derived from neuron-neuron co-activations. This view allows us to ask whether population-level structure is behaviorally meaningful, how it changes across modalities and depth, and whether it identifies causally influential internal components under intervention. We show that correlation topology carries recoverable behavioral signal; moreover, cross-modal structure progressively consolidates with depth around a compact set of recurrent hub neurons, whose targeted perturbation substantially alters model output. Neural topology thus emerges as a meaningful intermediate scale for VLM interpretability: richer than local attribution, more tractable than full circuit recovery, and empirically tied to multimodal behavior. Code is publicly available at https://github.com/he-h/vlm-graph-probing.

cs.CV↗

arXiv2026

Probing Neural Topology of Large Language Models

Probing large language models (LLMs) has yielded valuable insights into their internal mechanisms by linking neural activations to interpretable semantics. However, the complex mechanisms that link neuron's functional co-activation with the emergent model capabilities remains largely unknown, hindering a deeper understanding and safer development of LLMs. In this work, we introduce graph probing, a method for uncovering the functional connectivity of LLM neurons and relating it to language generation performance. By probing models across diverse LLM families and scales, we discover a universal predictability of language generation and understanding performance using only neural topology, which persists even when retaining just 1% of neuron connections. Strikingly, probing on topology outperforms probing on activation by up to 130.4% and 67.7% on perplexity and space/time semantic regression respectively, suggesting that neural topology contains orders of richer information of LLM performance than neural activation, which can be easily extracted with simple linear or MLP probes. To explain the dependence between neural topology and language performance, we identify default networks and hub neurons in LLMs and provide causal evidence by interventional experiments on multiple benchmarks, showing that LLMs actually exploit these topological information. Further analyses suggest that graph probing can be effectively leveraged to improve the efficiency and reliability of LLMs through proof-of-concept applications in model pruning and hallucination detection. Codes and data for the graph probing toolbox are available at https://github.com/DavyMorgan/llm-graph-probing.

cs.CL↗

arXiv2024

IG2: Integrated Gradient on Iterative Gradient Path for Feature Attribution

Feature attribution explains Artificial Intelligence (AI) at the instance level by providing importance scores of input features' contributions to model prediction. Integrated Gradients (IG) is a prominent path attribution method for deep neural networks, involving the integration of gradients along a path from the explained input (explicand) to a counterfactual instance (baseline). Current IG variants primarily focus on the gradient of explicand's output. However, our research indicates that the gradient of the counterfactual output significantly affects feature attribution as well. To achieve this, we propose Iterative Gradient path Integrated Gradients (IG2), considering both gradients. IG2 incorporates the counterfactual gradient iteratively into the integration path, generating a novel path (GradPath) and a novel baseline (GradCF). These two novel IG components effectively address the issues of attribution noise and arbitrary baseline choice in earlier IG methods. IG2, as a path method, satisfies many desirable axioms, which are theoretically justified in the paper. Experimental results on XAI benchmark, ImageNet, MNIST, TREC questions answering, wafer-map failure patterns, and CelebA face attributes validate that IG2 delivers superior feature attributions compared to the state-of-the-art techniques. The code is released at: https://github.com/JoeZhuo-ZY/IG2.

cs.CV↗

arXiv2023

ABIGX: A Unified Framework for eXplainable Fault Detection and Classification

For explainable fault detection and classification (FDC), this paper proposes a unified framework, ABIGX (Adversarial fault reconstruction-Based Integrated Gradient eXplanation). ABIGX is derived from the essentials of previous successful fault diagnosis methods, contribution plots (CP) and reconstruction-based contribution (RBC). It is the first explanation framework that provides variable contributions for the general FDC models. The core part of ABIGX is the adversarial fault reconstruction (AFR) method, which rethinks the FR from the perspective of adversarial attack and generalizes to fault classification models with a new fault index. For fault classification, we put forward a new problem of fault class smearing, which intrinsically hinders the correct explanation. We prove that ABIGX effectively mitigates this problem and outperforms the existing gradient-based explanation methods. For fault detection, we theoretically bridge ABIGX with conventional fault diagnosis methods by proving that CP and RBC are the linear specifications of ABIGX. The experiments evaluate the explanations of FDC by quantitative metrics and intuitive illustrations, the results of which show the general superiority of ABIGX to other advanced explanation methods.

cs.LG↗

arXiv2023

PatchProto Networks for Few-shot Visual Anomaly Classification

The visual anomaly diagnosis can automatically analyze the defective products, which has been widely applied in industrial quality inspection. The anomaly classification can classify the defective products into different categories. However, the anomaly samples are hard to access in practice, which impedes the training of canonical machine learning models. This paper studies a practical issue that anomaly samples for training are extremely scarce, i.e., few-shot learning (FSL). Utilizing the sufficient normal samples, we propose PatchProto networks for few-shot anomaly classification. Different from classical FSL methods, PatchProto networks only extract CNN features of defective regions of interest, which serves as the prototypes for few-shot learning. Compared with basic few-shot classifier, the experiment results on MVTec-AD dataset show PatchProto networks significantly improve the few-shot anomaly classification accuracy.

cs.CV↗

arXiv2021

Free-breathing 3D Cardiac T1 Mapping with Transmit B1 Correction at 3T

Purpose: To develop a cardiac T1 mapping method for free-breathing 3D T1 mapping of the whole heart at 3T with transmit B1 (B1+) correction Methods: A free-breathing, ECG-gated inversion recovery sequence with spoiled gradient-echo readout was developed and optimized for cardiac T1 mapping at 3T. High-frame rate dynamic images were reconstructed from sparse (k,t)-space data acquired along a stack-of-stars trajectory using a subspace-based method for accelerated imaging. Joint T1 and flip-angle (FA) estimation was performed in T1 mapping to improve its robustness to B1+ inhomogeneity. Subject-specific timing of data acquisition was utilized in the estimation to account for natural heart-rate variations during the imaging experiment. Results: Simulations showed that accuracy and precision of T1 mapping can be improved with joint T1 and FA estimation and optimized ECG-gated SPGR-based IR acquisition scheme. The phantom study showed good agreement between the T1 maps from the proposed method and the reference method. 3D cardiac T1 maps (40 slices) were obtained at a 1.9 mm in-plane and 4.5 mm through-plane spatial resolution from healthy subjects (n=6) with an average imaging time of 14.2 +- 1.6 min (heartbeat rate: 64.2 +- 7.1 bpm), showing myocardial T1 values comparable to those obtained from MOLLI. The proposed method generated B1+ maps with spatially smooth variation showing 21-32% and 11-15% variations across the septal-lateral and inferior-anterior regions of the myocardium in the left ventricle. Conclusion: The proposed method allows free-breathing 3D T1 mapping of the whole-heart with transmit B1 correction in a practical imaging time.

physics.med-ph↗

arXiv2021

Deep learning-based GTV contouring modeling inter- and intra- observer variability in sarcomas

Background and purpose: The delineation of the gross tumor volume (GTV) is a critical step for radiation therapy treatment planning. The delineation procedure is typically performed manually which exposes two major issues: cost and reproducibility. Delineation is a time-consuming process that is subject to inter- and intra-observer variability. While methods have been proposed to predict GTV contours, typical approaches ignore variability and therefore fail to utilize the valuable confidence information offered by multiple contours. Materials and methods: In this work we propose an automatic GTV contouring method for soft-tissue sarcomas from X-ray computed tomography (CT) images, using deep learning by integrating inter- and intra-observer variability in the learned model. Sixty-eight patients with soft tissue and bone sarcomas were considered in this evaluation, all underwent pre-operative CT imaging used to perform GTV delineation. Four radiation oncologists and radiologists performed three contouring trials each for all patients. We quantify variability by defining confidence levels based on the frequency of inclusion of a given voxel into the GTV and use a deep convolutional neural network to learn GTV confidence maps. Results: Results were compared to confidence maps from the four readers as well as ground-truth consensus contours established jointly by all readers. The resulting continuous Dice score between predicted and true confidence maps was 87% and the Hausdorff distance was 14 mm. Conclusion: Results demonstrate the ability of the proposed method to predict accurate contours while utilizing variability and as such it can be used to improve clinical workflow.

physics.med-ph↗

arXiv2021

Neural-Symbolic Commonsense Reasoner with Relation Predictors

Commonsense reasoning aims to incorporate sets of commonsense facts, retrieved from Commonsense Knowledge Graphs (CKG), to draw conclusion about ordinary situations. The dynamic nature of commonsense knowledge postulates models capable of performing multi-hop reasoning over new situations. This feature also results in having large-scale sparse Knowledge Graphs, where such reasoning process is needed to predict relations between new events. However, existing approaches in this area are limited by considering CKGs as a limited set of facts, thus rendering them unfit for reasoning over new unseen situations and events. In this paper, we present a neural-symbolic reasoner, which is capable of reasoning over large-scale dynamic CKGs. The logic rules for reasoning over CKGs are learned during training by our model. In addition to providing interpretable explanation, the learned logic rules help to generalise prediction to newly introduced events. Experimental results on the task of link prediction on CKGs prove the effectiveness of our model by outperforming the state-of-the-art models.

cs.AI↗

arXiv2020

COSMO: Conditional SEQ2SEQ-based Mixture Model for Zero-Shot Commonsense Question Answering

Commonsense reasoning refers to the ability of evaluating a social situation and acting accordingly. Identification of the implicit causes and effects of a social context is the driving capability which can enable machines to perform commonsense reasoning. The dynamic world of social interactions requires context-dependent on-demand systems to infer such underlying information. However, current approaches in this realm lack the ability to perform commonsense reasoning upon facing an unseen situation, mostly due to incapability of identifying a diverse range of implicit social relations. Hence they fail to estimate the correct reasoning path. In this paper, we present Conditional SEQ2SEQ-based Mixture model (COSMO), which provides us with the capabilities of dynamic and diverse content generation. We use COSMO to generate context-dependent clauses, which form a dynamic Knowledge Graph (KG) on-the-fly for commonsense reasoning. To show the adaptability of our model to context-dependant knowledge generation, we address the task of zero-shot commonsense question answering. The empirical results indicate an improvement of up to +5.2% over the state-of-the-art models.

cs.CL↗

arXiv2020

Accelerating MRI Reconstruction on TPUs

The advanced magnetic resonance (MR) image reconstructions such as the compressed sensing and subspace-based imaging are considered as large-scale, iterative, optimization problems. Given the large number of reconstructions required by the practical clinical usage, the computation time of these advanced reconstruction methods is often unacceptable. In this work, we propose using Google's Tensor Processing Units (TPUs) to accelerate the MR image reconstruction. TPU is an application-specific integrated circuit (ASIC) for machine learning applications, which has recently been used to solve large-scale scientific computing problems. As proof-of-concept, we implement the alternating direction method of multipliers (ADMM) in TensorFlow to reconstruct images on TPUs. The reconstruction is based on multi-channel, sparsely sampled, and radial-trajectory $k$-space data with sparsity constraints. The forward and inverse non-uniform Fourier transform operations are formulated in terms of matrix multiplications as in the discrete Fourier transform. The sparsifying transform and its adjoint operations are formulated as convolutions. The data decomposition is applied to the measured $k$-space data such that the aforementioned tensor operations are localized within individual TPU cores. The data decomposition and the inter-core communication strategy are designed in accordance with the TPU interconnect network topology in order to minimize the communication time. The accuracy and the high parallel efficiency of the proposed TPU-based image reconstruction method are demonstrated through numerical examples.

cs.CE↗

arXiv2019

Accessible quantitative phase imaging in confocal microscopy with sinusoidal-phase synthetic optical holography

We present a technically simple implementation of quantitative phase imaging in confocal microscopy based on synthetic optical holography with sinusoidal-phase reference waves. Using a Mirau interference objective and low-amplitude vertical sample vibration with a piezo-controlled stage, we record synthetic holograms on commercial confocal microscopes (Nikon, model: A1R; Zeiss: model: LSM-880), from which quantitative phase images are reconstructed. We demonstrate our technique by stain-free imaging of cervical (HeLa) and ovarian (ES-2) cancer cells and stem cell (mHAT9a) samples. Our technique has the potential to extend fluorescence imaging applications in confocal microscopy by providing label-free cell finding, monitoring cell morphology, as well as non-perturbing long-time observation of live cells based on quantitative phase contrast.

physics.optics↗