arXiv subjects

Liping Liu

Publications and source records attributed to Liping Liu.

At least 19 recordsLinked to original sources

arXiv2026

Towards Precision Therapy in Hepatocellular Carcinoma: A Clinical-Reasoning LLM for Risk Stratification and Treatment Guidance

Hepatocellular carcinoma (HCC) is a common malignancy and a leading cause of cancer-related mortality. Current guidelines and staging systems provide coarse categories, but often miss within-stage heterogeneity and the clinical context in electronic medical records (EMRs). We present HCC-STAR (Hepatocellular Carcinoma Staging, Treatment And pRognosis), a clinically aligned large language model that reads routine EMR narratives and jointly outputs risk score-based staging, ranked guideline-consistent treatments with evidence-based rationales, and individualized survival estimates. We curated about 30,000 HCC cases from SEER and expanded them into EMR-style narrative training data using a clinician-validated, prompt-based augmentation workflow. On this corpus, we developed a knowledge-aligned reasoning framework optimized with a step-verifiable composite reward, moving beyond text-level memorization of clinical guidelines. In a multi-center cohort of 6,668 patients from 12 hospitals in China, HCC-STAR achieved state-of-the-art performance in treatment recommendation and risk stratification compared with clinical guidelines and competitive models, including GPT-5 and Gemini-2.5 Pro. Hypothetical overall-survival analysis showed a median survival of 51 months under adherence to HCC-STAR recommendations, compared with 29 and 32 months under BCLC and CNLC. In clinician-centric evaluations, blinded hepatobiliary specialists rated HCC-STAR's reasoning and evidence-based justifications as trustworthy. The model surpassed resident and attending physicians in treatment accuracy and helped physicians make more accurate decisions faster when used as an assistant. These findings support HCC-STAR as a reliable and verifiable decision-support system for risk stratification and precision therapy in HCC.

cs.AI↗

arXiv2025

UltraTwin: Towards Cardiac Anatomical Twin Generation from Multi-view 2D Ultrasound

Echocardiography is routine for cardiac examination. However, 2D ultrasound (US) struggles with accurate metric calculation and direct observation of 3D cardiac structures. Moreover, 3D US is limited by low resolution, small field of view and scarce availability in practice. Constructing the cardiac anatomical twin from 2D images is promising to provide precise treatment planning and clinical quantification. However, it remains challenging due to the rare paired data, complex structures, and US noises. In this study, we introduce a novel generative framework UltraTwin, to obtain cardiac anatomical twin from sparse multi-view 2D US. Our contribution is three-fold. First, pioneered the construction of a real-world and high-quality dataset containing strictly paired multi-view 2D US and CT, and pseudo-paired data. Second, we propose a coarse-to-fine scheme to achieve hierarchical reconstruction optimization. Last, we introduce an implicit autoencoder for topology-aware constraints. Extensive experiments show that UltraTwin reconstructs high-quality anatomical twins versus strong competitors. We believe it advances anatomical twin modeling for potential applications in personalized cardiac care.

eess.IV↗

arXiv2025

Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction

Self-reflection for Large Language Models (LLMs) has gained significant attention. Existing approaches involve models iterating and improving their previous responses based on LLMs' internal reflection ability or external feedback. However, recent research has raised doubts about whether intrinsic self-correction without external feedback may even degrade performance. Based on our empirical evidence, we find that current static reflection methods may lead to redundant, drift, and stubborn issues. To mitigate this, we introduce Instruct-of-Reflection (IoRT), a novel and general reflection framework that leverages dynamic-meta instruction to enhance the iterative reflection capability of LLMs. Specifically, we propose the instructor driven by the meta-thoughts and self-consistency classifier, generates various instructions, including refresh, stop, and select, to guide the next reflection iteration. Our experiments demonstrate that IoRT achieves an average improvement of 10.1% over established baselines in mathematical and commonsense reasoning tasks, highlighting its efficacy and applicability.

cs.CL↗

arXiv2025

MADGEN: Mass-Spec attends to De Novo Molecular generation

The annotation (assigning structural chemical identities) of MS/MS spectra remains a significant challenge due to the enormous molecular diversity in biological samples and the limited scope of reference databases. Currently, the vast majority of spectral measurements remain in the "dark chemical space" without structural annotations. To improve annotation, we propose MADGEN (Mass-spec Attends to De Novo Molecular GENeration), a scaffold-based method for de novo molecular structure generation guided by mass spectrometry data. MADGEN operates in two stages: scaffold retrieval and spectra-conditioned molecular generation starting with the scaffold. In the first stage, given an MS/MS spectrum, we formulate scaffold retrieval as a ranking problem and employ contrastive learning to align mass spectra with candidate molecular scaffolds. In the second stage, starting from the retrieved scaffold, we employ the MS/MS spectrum to guide an attention-based generative model to generate the final molecule. Our approach constrains the molecular generation search space, reducing its complexity and improving generation accuracy. We evaluate MADGEN on three datasets (NIST23, CANOPUS, and MassSpecGym) and evaluate MADGEN's performance with a predictive scaffold retriever and with an oracle retriever. We demonstrate the effectiveness of using attention to integrate spectral information throughout the generation process to achieve strong results with the oracle retriever.

cs.LG↗

arXiv2024

ALKPU: an active learning method for the DeePMD model with Kalman filter

Neural network force field models such as DeePMD have enabled highly efficient large-scale molecular dynamics simulations with ab initio accuracy. However, building such models heavily depends on the training data obtained by costly electronic structure calculations, thereby it is crucial to carefully select and label the most representative configurations during model training to improve both extrapolation capability and training efficiency. To address this challenge, based on the Kalman filter theory we propose the Kalman Prediction Uncertainty (KPU) to quantify uncertainty of the model's prediction. With KPU we design the Active Learning by KPU (ALKPU) method, which can efficiently select representative configurations that should be labelled during model training. We prove that ALKPU locally leads to the fastest reduction of model's uncertainty, which reveals its rationality as a general active learning method. We test the ALKPU method using various physical system simulations and demonstrate that it can efficiently coverage the system's configuration space. Our work demonstrates the benefits of ALKPU as a novel active learning method, enhancing training efficiency and reducing computational resource demands.

physics.comp-ph↗

arXiv2024

SkipSNN: Efficiently Classifying Spike Trains with Event-attention

Spike train classification has recently become an important topic in the machine learning community, where each spike train is a binary event sequence with \emph{temporal-sparsity of signals of interest} and \emph{temporal-noise} properties. A promising model for it should follow the design principle of performing intensive computation only when signals of interest appear. So such tasks use mainly Spiking Neural Networks (SNNs) due to their consideration of temporal-sparsity of spike trains. However, the basic mechanism of SNNs ignore the temporal-noise issue, which makes them computationally expensive and thus high power consumption for analyzing spike trains on resource-constrained platforms. As an event-driven model, an SNN neuron makes a reaction given any input signals, making it difficult to quickly find signals of interest. In this paper, we introduce an event-attention mechanism that enables SNNs to dynamically highlight useful signals of the original spike trains. To this end, we propose SkipSNN, which extends existing SNN models by learning to mask out noise by skipping membrane potential updates and shortening the effective size of the computational graph. This process is analogous to how people choose to open and close their eyes to filter the information they see. We evaluate SkipSNN on various neuromorphic tasks and demonstrate that it achieves significantly better computational efficiency and classification accuracy than other state-of-the-art SNNs.

cs.NE↗

arXiv2024

Enhancing Diffusion-based Point Cloud Generation with Smoothness Constraint

Diffusion models have been popular for point cloud generation tasks. Existing works utilize the forward diffusion process to convert the original point distribution into a noise distribution and then learn the reverse diffusion process to recover the point distribution from the noise distribution. However, the reverse diffusion process can produce samples with non-smooth points on the surface because of the ignorance of the point cloud geometric properties. We propose alleviating the problem by incorporating the local smoothness constraint into the diffusion framework for point cloud generation. Experiments demonstrate the proposed model can generate realistic shapes and smoother point clouds, outperforming multiple state-of-the-art methods.

cs.CV↗

arXiv2024

Graph Pruning for Enumeration of Minimal Unsatisfiable Subsets

Finding Minimal Unsatisfiable Subsets (MUSes) of binary constraints is a common problem in infeasibility analysis of over-constrained systems. However, because of the exponential search space of the problem, enumerating MUSes is extremely time-consuming in real applications. In this work, we propose to prune formulas using a learned model to speed up MUS enumeration. We represent formulas as graphs and then develop a graph-based learning model to predict which part of the formula should be pruned. Importantly, our algorithm does not require data labeling by only checking the satisfiability of pruned formulas. It does not even require training data from the target application because it extrapolates to data with different distributions. In our experiments we combine our algorithm with existing MUS enumerators and validate its effectiveness in multiple benchmarks including a set of real-world problems outside our training distribution. The experiment results show that our method significantly accelerates MUS enumeration on average on these benchmark problems.

cs.AI↗

arXiv2023

Development of a Deep Learning System for Intra-Operative Identification of Cancer Metastases

For several cancer patients, operative resection with curative intent can end up in early recurrence of the cancer. Current limitations in peri-operative cancer staging and especially intra-operative misidentification of visible metastases is likely the main reason leading to unnecessary operative interventions in the affected individuals. Here, we evaluate whether an artificial intelligence (AI) system can improve recognition of peritoneal surface metastases on routine staging laparoscopy images from patients with gastrointestinal malignancies. In a simulated setting evaluating biopsied peritoneal lesions, a prototype deep learning surgical guidance system outperformed oncologic surgeons in identifying peritoneal surface metastases. In this environment the developed AI model would have improved the identification of metastases by 5% while reducing the number of unnecessary biopsies by 28% compared to current standard practice. Evaluating non-biopsied peritoneal lesions, the findings support the possibility that the AI system could identify peritoneal surface metastases that were falsely deemed benign in clinical practice. Our findings demonstrate the technical feasibility of an AI system for intra-operative identification of peritoneal surface metastases, but require future assessment in a multi-institutional clinical setting.

eess.IV↗

arXiv2022

Interpretable Node Representation with Attribute Decoding

Variational Graph Autoencoders (VGAEs) are powerful models for unsupervised learning of node representations from graph data. In this work, we systematically analyze modeling node attributes in VGAEs and show that attribute decoding is important for node representation learning. We further propose a new learning model, interpretable NOde Representation with Attribute Decoding (NORAD). The model encodes node representations in an interpretable approach: node representations capture community structures in the graph and the relationship between communities and node attributes. We further propose a rectifying procedure to refine node representations of isolated notes, improving the quality of these nodes' representations. Our empirical results demonstrate the advantage of the proposed model when learning graph data in an interpretable approach.

cs.LG↗

arXiv2022

Diffusion of microstructured anisotropic particles in an external field

Microstructured particles are widely used in industries and state-of-the-art research and development. Diffusion of particles, particularly, controlled diffusion by a remotely applied field, has inspired novel applications ranging from targeted drug deliveries, novel procedures for quantifying physical properties of nanoparticles and ambient fluids, to fabrication of composites with enhanced properties. In this work, we report a systematic analysis on field-controlled diffusion of microstructured particles. In account of shape anisotropy and structural heterogeneity of a particle, we study coupled Brownian motions of the particle in $\mathbb{R}^3\times$SO(3). Starting from the microscopic stochastic differential equations of motions, we achieve the coarse-grained Fokker-Planck equation that governs the evolution of the probability distribution function with respect to the position and orientation of the particle. Under some mild conditions, we identify the long-time diffusivity for microstructured particles in an external field. The formulation is applicable to microstructured particles of arbitrary shapes and heterogeneities. As examples of applications, we analyze the diffusion of a heterogeneous spheroidal particle and a pair of spheroidal particles bonded by an elastic ligament. For heterogeneous spheroidal particles, we obtain explicit generalized Stokes-Einstein's relations for diffusivity that accounts for the effects of shape anisotropy, heterogeneity, and an external alignment field. For pairs of spheroidal particles, we consider the superimposed relaxation process from an initial non-equilibrium state to the final equilibrium state. The anomalous scaling of Mean Square Displacement (MSD) with respect to the time of such processes may provide important insight for understanding anomalous diffusions observed in migration of macromolecules and cells in complex viscoelastic media.

cond-mat.soft↗

arXiv2022

Deterministic Dynamic Stackelberg Games: Time-Consistent Open-Loop Solution

In this paper, the known deterministic linear-quadratic Stackelberg game is revisited, whose open-loop Stackelberg solution actually possesses the nature of time inconsistency. To handle this time inconsistency, {a two-tier game framework is introduced, where the upper-tier game works according to Stackelberg's scenario with a leader and a follower, and two lower-tier intertemporal games give the follower's and leader's equilibrium response mappings that mimic the notion of time-consistent open-loop equilibrium control in existing literature. The resulting open-loop equilibrium solution of the two-tier game} is shown to be weakly time-consistent in the sense that the adopted policies will no longer be denied in the future only if past policies are consistent with the equilibrium policies. On the existence and uniqueness of such a solution, necessary and sufficient conditions are obtained, which are characterized via the solutions of several Riccati-like equations.

math.OC↗

arXiv2021

DiaKG: an Annotated Diabetes Dataset for Medical Knowledge Graph Construction

Knowledge Graph has been proven effective in modeling structured information and conceptual knowledge, especially in the medical domain. However, the lack of high-quality annotated corpora remains a crucial problem for advancing the research and applications on this task. In order to accelerate the research for domain-specific knowledge graphs in the medical domain, we introduce DiaKG, a high-quality Chinese dataset for Diabetes knowledge graph, which contains 22,050 entities and 6,890 relations in total. We implement recent typical methods for Named Entity Recognition and Relation Extraction as a benchmark to evaluate the proposed dataset thoroughly. Empirical results show that the DiaKG is challenging for most existing methods and further analysis is conducted to discuss future research direction for improvements. We hope the release of this dataset can assist the construction of diabetes knowledge graphs and facilitate AI-based applications.

cs.CL↗

arXiv2021

New extremal inclusions and their applications to two-phase composites

In this paper, we find a class of special inclusions that have the same property with respect to second order linear partial differential equations as holds for ellipsoids. That is, in the simplest case and in physical terms, constant magnetization of the inclusion implies constant magnetic field on the inclusion. The special inclusions are found as solutions of a simple variational inequality. This variational inequality allows us to prescribe the connectivity and periodicity properties of the inclusions. For example we find periodic arrays of inclusions in two and three dimensions for which constant magnetization of the inclusions implies constant magnetic field on the inclusions. The volume fraction of the inclusions can be any number between zero and one. We find such inclusions with any finite number of components and components that are multiply connected. These special inclusions enjoy many useful properties with respect to homogenization and energy minimization. For example, we use them to give new results on a) the effective properties of two-phase composites and b) optimal bounds and optimal microstructures for two-phase composites.

math.AP↗

arXiv2021

Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation

A graph generative model defines a distribution over graphs. One type of generative model is constructed by autoregressive neural networks, which sequentially add nodes and edges to generate a graph. However, the likelihood of a graph under the autoregressive model is intractable, as there are numerous sequences leading to the given graph; this makes maximum likelihood estimation challenging. Instead, in this work we derive the exact joint probability over the graph and the node ordering of the sequential process. From the joint, we approximately marginalize out the node orderings and compute a lower bound on the log-likelihood using variational inference. We train graph generative models by maximizing this bound, without using the ad-hoc node orderings of previous methods. Our experiments show that the log-likelihood bound is significantly tighter than the bound of previous schemes. Moreover, the models fitted with the proposed algorithm can generate high-quality graphs that match the structures of target graphs not seen during training. We have made our code publicly available at \hyperref[https://github.com/tufts-ml/graph-generation-vi]{https://github.com/tufts-ml/graph-generation-vi}.

stat.ML↗

arXiv2020

E2 distribution and statistical regularity in polygonal planar tessellations

From solar supergranulation to salt flat in Bolivia, from veins on leaves to cells on Drosophila wing discs, polygon-based networks exhibit great complexities, yet similarities persist and statistical distributions can be remarkably consistent. Based on analysis of 99 polygonal tessellations of a wide variety of physical origins, this work demonstrates the ubiquity of an exponential distribution in the squared norm of the deformation tensor, $E^{2}$, which directly leads to the ubiquitous presence of Gamma distributions in polygon aspect ratio. The $E^{2}$ distribution in turn arises as a $χ^{2}$-distribution, and an analytical framework is developed to compute its statistics. $E^{2}$ is closely related to many energy forms, and its Boltzmann-like feature allows the definition of a pseudo-temperature. Together with normality in other key variables such as vertex displacement, this work reveals regularities universally present in all systems alike

cond-mat.stat-mech↗

arXiv2020

Using Graph Neural Networks for Mass Spectrometry Prediction

Detecting and quantifying products of cellular metabolism using Mass Spectrometry (MS) has already shown great promise in many biological and biomedical applications. The biggest challenge in metabolomics is annotation, where measured spectra are assigned chemical identities. Despite advances, current methods provide limited annotation for measured spectra. Here, we explore using graph neural networks (GNNs) to predict the spectra. The input to our model is a molecular graph. The model is trained and tested on the NIST 17 LC-MS dataset. We compare our results to NEIMS, a neural network model that utilizes molecular fingerprints as inputs. Our results show that GNN-based models offer higher performance than NEIMS. Importantly, we show that ranking results heavily depend on the candidate set size and on the similarity of the candidates to the target molecule, thus highlighting the need for consistent, well-characterized evaluation protocols for this domain.

cs.LG↗

arXiv2020

DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks

Transfer learning through fine-tuning a pre-trained neural network with an extremely large dataset, such as ImageNet, can significantly accelerate training while the accuracy is frequently bottlenecked by the limited dataset size of the new target task. To solve the problem, some regularization methods, constraining the outer layer weights of the target network using the starting point as references (SPAR), have been studied. In this paper, we propose a novel regularized transfer learning framework DELTA, namely DEep Learning Transfer using Feature Map with Attention. Instead of constraining the weights of neural network, DELTA aims to preserve the outer layer outputs of the target network. Specifically, in addition to minimizing the empirical loss, DELTA intends to align the outer layer outputs of two networks, through constraining a subset of feature maps that are precisely selected by attention that has been learned in an supervised learning manner. We evaluate DELTA with the state-of-the-art algorithms, including L2 and L2-SP. The experiment results show that our proposed method outperforms these baselines with higher accuracy for new tasks.

cs.LG↗