arXiv subjects

Ke Lu

Publications and source records attributed to Ke Lu.

At least 19 recordsLinked to original sources

arXiv2026

Develop and Optimize 5DCT Imaging Simulation and Reconstruction Methods

Purpose: To develop and optimize a 5DCT (3D + cardiac phase + respiratory phase) imaging simulation and reconstruction pipeline, and to compare two sinogram-space interpolation methods for reconstructing images at arbitrary combinations of cardiac and respiratory phase. Methods: Helical CT projections were simulated from the 4D XCAT phantom across a range of cardiac and respiratory motion states, with Poisson and electronic noise added. Ground-truth-matched volumes were generated at 5 cardiac phases and 10 respiratory amplitudes (50 total phase combinations). Because acquired projections are sparsely and unevenly distributed across this joint phase space, each target slice was reconstructed by interpolating rebinned sinogram rows to the target cardiac phase and respiratory amplitude, using either 2D scattered barycentric interpolation or 2D scattered local linear interpolation with a circular kernel for cardiac phase. Reconstructed volumes were compared to phantom ground truth using mean absolute error (MAE), and to conventional respiratory-gated 4DCT (r4DCT) reconstructed from the same simulated data. Results: Both interpolation methods eliminated the severe axial misalignment artifacts present when helical projections were reconstructed without phase-space interpolation. Local linear interpolation achieved lower MAE than barycentric interpolation across most tested conditions, with the largest improvement at low pitch. The 5DCT pipeline also produced respiratory-only volumes with fewer residual cardiac-motion artifacts than conventional r4DCT reconstructed from the same projection data, including at standard clinical pitch (0.1). Conclusions: 5DCT reconstruction using sinogram-space interpolation is feasible and can jointly resolve cardiac and respiratory motion with better accuracy than conventional 4DCT reconstruction.

physics.med-ph↗

arXiv2026

Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding

Generative Vision-Language Models (VLMs) commonly treat bounding-box coordinates as independent output symbols, leaving numerical order and axis semantics implicit. We identify this representation as an important source of error in visual grounding. Hi-Token encodes each coordinate with axis-specific tokens for the hundreds, tens, and ones digits, which adds coarse-to-fine structure and increases token reuse while retaining the existing VLM architecture. Hi-GAR complements this representation with a geometry-based reward for Group Relative Policy Optimization (GRPO), using box overlap and coordinate accuracy at multiple scales. Controlled comparisons under matched training conditions show that Hi-Token improves localization throughout the evaluated IoU range. Hi-GAR further reduces low-overlap predictions and is used only during training. Experiments on three VLM backbones and the RefCOCO family show consistent gains across models and benchmarks. Hi-R1 achieves higher values than strong specialist baselines on most reported metrics. Analyses of token frequency, digit boundaries, object scale, and IoU distributions explain the effects of coordinate representation and reward training. The results show that structured coordinate generation provides an effective approach to generative visual grounding. Project page: https://xyzzzh.github.io/Hi-Token/

cs.CV↗

arXiv2026

IoU-PD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models

Visual grounding with multimodal large language models is commonly formulated as autoregressive coordinate generation, where a model outputs bounding-box coordinates as text given an image and a referring-expression prompt. While this interface is simple and compatible with instruction following, it introduces a mismatch between training and evaluation: training optimizes token-level likelihood over coordinate strings, whereas grounding quality is measured by geometric overlap. We propose IoU-PD, an IoU-aware privileged distillation method for coordinate-generating multimodal large language models. IoU-PD uses ground-truth boxes not only as coordinate targets, but also as privileged training-time guidance. During training, the student receives the original image and prompt, while a frozen teacher receives a box-marked image and an augmented prompt that indicates the marked region. The student is trained with a supervised fine-tuning anchor and a privileged distillation loss whose token weights reflect both geometric importance and teacher reliability. At inference time, IoU-PD requires no box overlay, privileged hint, teacher branch, or additional prediction module. Experiments on standard referring-expression grounding benchmarks show consistent region-level improvements over strong coordinate-generating baselines, demonstrating that ground-truth boxes can provide useful privileged guidance beyond serving as coordinate labels. Project page: https://xyzzzh.github.io/IoU-PD/

cs.CV↗

arXiv2026

DiffLens: A Visualization System to Explore Local Differences in Graph Sampling

Graph sampling techniques have been widely used to simplify network computation and visualization, which also results in inevitable differences between the sampled networks and the original networks in terms of nodes, edges and structures. Investigating such differences can inform graph sampling technique users of the pros and cons of different techniques and select the appropriate one, and can also help graph sampling developers evaluate their own technique. However, there are still no systematic ways to achieve such a goal. This paper fills this research gap by first proposing systematic and generic quantitative measures to quantify three categories of graph differences (i.e., neighbor-based, path-based, and structure-based). Built upon this, we further propose DiffLens, a novel visualization system to help graph sampling developers and users intuitively explore local differences at different regions of their interest within a sampled graph, where three new lens-based visual designs are presented to display the neighbor-based, path-based, and structure-based differences respectively. We conducted two case studies and a user study using real-world network datasets to evaluate DiffLens. The results confirmed its effectiveness and usability in helping users explore local differences and compare different graph sampling strategies.

cs.HC↗

arXiv2026

QueryGaussian: Scalable and Training-Free Open-Vocabulary 3D Instance Retrieval

Efficiently retrieving specific 3D instances from large-scale scenes via natural language prompts remains a formidable challenge in multimedia analysis. Existing approaches predominantly follow a "scene-level embedding" paradigm, which requires distilling high-dimensional semantic features into every 3D primitive. This strategy suffers from a fundamental architectural bottleneck: memory and computational costs scale linearly with scene complexity, inevitably triggering out-of-memory (OOM) failures in city-scale environments. To address this barrier, we propose QueryGaussian, a training-free framework for expeditious and scalable open-vocabulary 3D instance retrieval. Unlike holistic semantic distillation, QueryGaussian employs an instance-level query mechanism that decouples semantic understanding from geometric representation. Specifically, we leverage pre-trained 2D vision models to interpret user prompts and lift segmentation masks into 3D via a concurrent maximum-weight association strategy, ensuring semantic-visual consistency. To mitigate projection ambiguity, we introduce a temporal fusion module with multi-stage adaptive density clustering. Experimental results demonstrate that QueryGaussian not only matches the accuracy of state-of-the-art methods but also delivers a decisive efficiency leap, reducing GPU memory usage by over 70% and accelerating inference by 180x. Crucially, QueryGaussian enables expeditious instance retrieval on city-scale scenes containing tens of millions of Gaussians using consumer-grade hardware.

cs.CV↗

arXiv2026

Dual Causal Inference: Integrating Backdoor Adjustment and Instrumental Variable Learning for Medical VQA

Medical Visual Question Answering (MedVQA) aims to generate clinically reliable answers conditioned on complex medical images and questions. However, existing methods often overfit to superficial cross-modal correlations, neglecting the intrinsic biases embedded in multimodal medical data. Consequently, models become vulnerable to cross-modal confounding effects, severely hindering their ability to provide trustworthy diagnostic reasoning. To address this limitation, we propose a novel Dual Causal Inference (DCI) framework for MedVQA. To the best of our knowledge, DCI is the first unified architecture that integrates Backdoor Adjustment (BDA) and Instrumental Variable (IV) learning to jointly tackle both observable and unobserved confounders. Specifically, we formulate a Structural Causal Model (SCM) where observable cross-modal biases (e.g., frequent visual and textual co-occurrences) are mitigated via BDA, while unobserved confounders are compensated using an IV learned from a shared latent space. To guarantee the validity of the IV, we design mutual information constraints that maximize its dependence on the fused multimodal representations while minimizing its associations with the unobserved confounders and target answers. Through this dual mechanism, DCI extracts deconfounded representations that capture genuine causal relationships. Extensive experiments on four benchmark datasets, SLAKE, SLAKE-CP, VQA-RAD, and PathVQA, demonstrate that our method consistently outperforms existing approaches, particularly in out-of-distribution (OOD) generalization. Furthermore, qualitative analyses confirm that DCI significantly enhances the interpretability and robustness of cross-modal reasoning by explicitly disentangling true causal effects from spurious cross-modal shortcuts.

cs.CV↗

arXiv2026

Clinically Interpretable Sepsis Early Warning via LLM-Guided Simulation of Temporal Physiological Dynamics

Timely and interpretable early warning of sepsis remains a major clinical challenge due to the complex temporal dynamics of physiological deterioration. Traditional data-driven models often provide accurate yet opaque predictions, limiting physicians' confidence and clinical applicability. To address this limitation, we propose a Large Language Model (LLM)-guided temporal simulation framework that explicitly models physiological trajectories prior to disease onset for clinically interpretable prediction. The framework consists of a spatiotemporal feature extraction module that captures dynamic dependencies among multivariate vital signs, a Medical Prompt-as-Prefix module that embeds clinical reasoning cues into LLMs, and an agent-based post-processing component that constrains predictions within physiologically plausible ranges. By first simulating the evolution of key physiological indicators and then classifying sepsis onset, our model offers transparent prediction mechanisms that align with clinical judgment. Evaluated on the MIMIC-IV and eICU databases, the proposed method achieves superior AUC scores (0.861-0.903) across 24-4-hour pre-onset prediction tasks, outperforming conventional deep learning and rule-based approaches. More importantly, it provides interpretable trajectories and risk trends that can assist clinicians in early intervention and personalized decision-making in intensive care environments.

cs.LG↗

arXiv2026

Decoupled Hierarchical Distillation for Multimodal Emotion Recognition

Human multimodal emotion recognition (MER) seeks to infer human emotions by integrating information from language, visual, and acoustic modalities. Although existing MER approaches have achieved promising results, they still struggle with inherent multimodal heterogeneities and varying contributions from different modalities. To address these challenges, we propose a novel framework, Decoupled Hierarchical Multimodal Distillation (DHMD). DHMD decouples each modality's features into modality-irrelevant (homogeneous) and modality-exclusive (heterogeneous) components using a self-regression mechanism. The framework employs a two-stage knowledge distillation (KD) strategy: (1) coarse-grained KD via a Graph Distillation Unit (GD-Unit) in each decoupled feature space, where a dynamic graph facilitates adaptive distillation among modalities, and (2) fine-grained KD through a cross-modal dictionary matching mechanism, which aligns semantic granularities across modalities to produce more discriminative MER representations. This hierarchical distillation approach enables flexible knowledge transfer and effectively improves cross-modal feature alignment. Experimental results demonstrate that DHMD consistently outperforms state-of-the-art MER methods, achieving 1.3\%/2.4\% (ACC$_7$), 1.3\%/1.9\% (ACC$_2$) and 1.9\%/1.8\% (F1) relative improvement on CMU-MOSI/CMU-MOSEI dataset, respectively. Meanwhile, visualization results reveal that both the graph edges and dictionary activations in DHMD exhibit meaningful distribution patterns across modality-irrelevant/-exclusive feature spaces.

cs.CV↗

arXiv2026

Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives

Autonomous scientific discovery with large language model (LLM)-based agents has recently made substantial progress, demonstrating the ability to automate end-to-end research workflows. However, existing systems largely rely on runtime-centric execution paradigms, repeatedly reading, summarizing, and reasoning over large volumes of scientific literature online. This on-the-spot computation strategy incurs high computational cost, suffers from context window limitations, and often leads to brittle reasoning and hallucination. We propose Idea2Story, a pre-computation-driven framework for autonomous scientific discovery that shifts literature understanding from online reasoning to offline knowledge construction. Idea2Story continuously collects peer-reviewed papers together with their review feedback, extracts core methodological units, composes reusable research patterns, and organizes them into a structured methodological knowledge graph. At runtime, underspecified user research intents are aligned to established research paradigms, enabling efficient retrieval and reuse of high-quality research patterns instead of open-ended generation and trial-and-error. By grounding research planning and execution in a pre-built knowledge graph, Idea2Story alleviates the context window bottleneck of LLMs and substantially reduces repeated runtime reasoning over literature. We conduct qualitative analyses and preliminary empirical studies demonstrating that Idea2Story can generate coherent, methodologically grounded, and novel research patterns, and can produce several high-quality research demonstrations in an end-to-end setting. These results suggest that offline knowledge construction provides a practical and scalable foundation for reliable autonomous scientific discovery.

cs.CE↗

arXiv2025

Enhancing Black-Litterman Portfolio via Hybrid Forecasting Model Combining Multivariate Decomposition and Noise Reduction

Modern portfolio construction demands robust methods for integrating data-driven insights into asset allocation. The Black-Litterman model offers a powerful Bayesian approach to adjust equilibrium returns using investor views to form a posterior expectation along with market priors. Mainstream research mainly generates subjective views through statistical models or machine learning methods, among which hybrid models combined with decomposition algorithms perform well. However, most hybrid models do not pay enough attention to noise, and time series decomposition methods based on single variables make it difficult to fully utilize information between multiple variables. Multivariate decomposition also has problems of low efficiency and poor component quality. In this study, we propose a novel hybrid forecasting model SSA-MAEMD-TCN to automate and improve the view generation process. The proposed model combines Singular Spectrum Analysis (SSA) for denoising, Multivariate Aligned Empirical Mode Decomposition (MA-EMD) for frequency-aligned decomposition, and Temporal Convolutional Networks (TCNs) for deep sequence learning to capture complex temporal patterns across multiple financial indicators. Empirical tests on the Nasdaq 100 Index stocks show a significant improvement in forecasting performance compared to baseline models based on MAEMD and MEMD. The optimized portfolio performs well, with annualized returns and Sharpe ratios far exceeding those of the traditional portfolio over a short holding period, even after accounting for transaction costs.

cs.CE↗

arXiv2025

LoCA: Location-Aware Cosine Adaptation for Parameter-Efficient Fine-Tuning

Low-rank adaptation (LoRA) has become a prevalent method for adapting pre-trained large language models to downstream tasks. However, the simple low-rank decomposition form may constrain the hypothesis space. To address this limitation, we introduce Location-aware Cosine Adaptation (LoCA), a novel frequency-domain parameter-efficient fine-tuning method based on inverse Discrete Cosine Transform (iDCT) with selective locations of learnable components. We begin with a comprehensive theoretical comparison between frequency-domain and low-rank decompositions for fine-tuning pre-trained large models. Our analysis reveals that frequency-domain decomposition with carefully selected frequency components can surpass the expressivity of traditional low-rank-based methods. Furthermore, we demonstrate that iDCT offers a more efficient implementation compared to inverse Discrete Fourier Transform (iDFT), allowing for better selection and tuning of frequency components while maintaining equivalent expressivity to the optimal iDFT-based adaptation. By employing finite-difference approximation to estimate gradients for discrete locations of learnable coefficients on the DCT spectrum, LoCA dynamically selects the most informative frequency components during training. Experiments on diverse language and vision fine-tuning tasks demonstrate that LoCA offers enhanced parameter efficiency while maintains computational feasibility comparable to low-rank-based methods.

cs.LG↗

arXiv2024

One Pot Synthesis of Cubic Gauche Polymeric Nitrogen

The long sought cubic gauche polymeric nitrogen (cg-N) consisting of N-N single bonds has been synthesized by a simple route using sodium azide as a precursor at ambient conditions. The recrystallization process was designed to expose crystal faces with low activation energy that facilitates initiating the polymeric reaction at ambient conditions. The azide was considered as a precursor due to the low energy barrier in transforming double bonded N=N to single bonded cg-N. Raman spectrum measurements detected the emerging vibron peaks at 635 cm-1 for the polymerized sodium azide samples, demonstrating the formation of cg-N with N-N single bonds. Different from traditional high pressure technique and recently developed plasma enhanced chemical vapor deposition method, the route achieves the quantitative synthesis of cg-N at ambient conditions. The simple method to synthesize cg-N offers potential for further scale up production as well as practical applications of polymeric nitrogen based materials as high energy density materials.

cond-mat.mtrl-sci↗

arXiv2024

MambaDETR: Query-based Temporal Modeling using State Space Model for Multi-View 3D Object Detection

Utilizing temporal information to improve the performance of 3D detection has made great progress recently in the field of autonomous driving. Traditional transformer-based temporal fusion methods suffer from quadratic computational cost and information decay as the length of the frame sequence increases. In this paper, we propose a novel method called MambaDETR, whose main idea is to implement temporal fusion in the efficient state space. Moreover, we design a Motion Elimination module to remove the relatively static objects for temporal fusion. On the standard nuScenes benchmark, our proposed MambaDETR achieves remarkable result in the 3D object detection task, exhibiting state-of-the-art performance among existing temporal fusion methods.

cs.CV↗

arXiv2024

A facile route to synthesize cubic gauche polymeric nitrogen

In this work, the long-sought cg-N with N-N single bond has been synthesized for the first time by a thermal-driven-only chemical route at ambient conditions. The successful synthesis of cg-N was achieved by first creating a solution of azides, which was then pretreated under vacuum conditions. Following the pretreatment, the resultant concentrated azide was heated at temperatures ranging from 260{\deg}C to 330{\deg}C for a reaction time of 3 hours, ultimately leading to the formation of cg-N. The emergent intense Raman peak characterized of cg-N provides solid evidence that the double bonded nitrogen-nitrogen transforms into a single bond form, which agrees well with cg-N structure. To date, this is the only work achieving the quantity of cg-N synthesized at ambient conditions by a facile route that can be further developed for the scalable synthesis and applications of polymerized nitrogen-based materials as high energy density materials.

cond-mat.mtrl-sci↗

arXiv2024

MVLLaVA: An Intelligent Agent for Unified and Flexible Novel View Synthesis

This paper introduces MVLLaVA, an intelligent agent designed for novel view synthesis tasks. MVLLaVA integrates multiple multi-view diffusion models with a large multimodal model, LLaVA, enabling it to handle a wide range of tasks efficiently. MVLLaVA represents a versatile and unified platform that adapts to diverse input types, including a single image, a descriptive caption, or a specific change in viewing azimuth, guided by language instructions for viewpoint generation. We carefully craft task-specific instruction templates, which are subsequently used to fine-tune LLaVA. As a result, MVLLaVA acquires the capability to generate novel view images based on user instructions, demonstrating its flexibility across diverse tasks. Experiments are conducted to validate the effectiveness of MVLLaVA, demonstrating its robust performance and versatility in tackling diverse novel view synthesis challenges.

cs.CV↗

arXiv2024

ExpLLM: Towards Chain of Thought for Facial Expression Recognition

Facial expression recognition (FER) is a critical task in multimedia with significant implications across various domains. However, analyzing the causes of facial expressions is essential for accurately recognizing them. Current approaches, such as those based on facial action units (AUs), typically provide AU names and intensities but lack insight into the interactions and relationships between AUs and the overall expression. In this paper, we propose a novel method called ExpLLM, which leverages large language models to generate an accurate chain of thought (CoT) for facial expression recognition. Specifically, we have designed the CoT mechanism from three key perspectives: key observations, overall emotional interpretation, and conclusion. The key observations describe the AU's name, intensity, and associated emotions. The overall emotional interpretation provides an analysis based on multiple AUs and their interactions, identifying the dominant emotions and their relationships. Finally, the conclusion presents the final expression label derived from the preceding analysis. Furthermore, we also introduce the Exp-CoT Engine, designed to construct this expression CoT and generate instruction-description data for training our ExpLLM. Extensive experiments on the RAF-DB and AffectNet datasets demonstrate that ExpLLM outperforms current state-of-the-art FER methods. ExpLLM also surpasses the latest GPT-4o in expression CoT generation, particularly in recognizing micro-expressions where GPT-4o frequently fails.

cs.CV↗

arXiv2024

Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation

Large vision-language models (VLMs) like CLIP have demonstrated good zero-shot learning performance in the unsupervised domain adaptation task. Yet, most transfer approaches for VLMs focus on either the language or visual branches, overlooking the nuanced interplay between both modalities. In this work, we introduce a Unified Modality Separation (UniMoS) framework for unsupervised domain adaptation. Leveraging insights from modality gap studies, we craft a nimble modality separation network that distinctly disentangles CLIP's features into language-associated and vision-associated components. Our proposed Modality-Ensemble Training (MET) method fosters the exchange of modality-agnostic information while maintaining modality-specific nuances. We align features across domains using a modality discriminator. Comprehensive evaluations on three benchmarks reveal our approach sets a new state-of-the-art with minimal computational costs. Code: https://github.com/TL-UESTC/UniMoS

cs.CV↗

arXiv2024

Agile Multi-Source-Free Domain Adaptation

Efficiently utilizing rich knowledge in pretrained models has become a critical topic in the era of large models. This work focuses on adaptively utilizing knowledge from multiple source-pretrained models to an unlabeled target domain without accessing the source data. Despite being a practically useful setting, existing methods require extensive parameter tuning over each source model, which is computationally expensive when facing abundant source domains or larger source models. To address this challenge, we propose a novel approach which is free of the parameter tuning over source backbones. Our technical contribution lies in the Bi-level ATtention ENsemble (Bi-ATEN) module, which learns both intra-domain weights and inter-domain ensemble weights to achieve a fine balance between instance specificity and domain consistency. By slightly tuning source bottlenecks, we achieve comparable or even superior performance on a challenging benchmark DomainNet with less than 3% trained parameters and 8 times of throughput compared with SOTA method. Furthermore, with minor modifications, the proposed module can be easily equipped to existing methods and gain more than 4% performance boost. Code is available at https://github.com/TL-UESTC/Bi-ATEN.

cs.CV↗