Xiaojun Ye

Mengling Deng, Yuanpeng Chen, Sheng Yang et al.

Vision-language models (VLMs) have demonstrated strong applicability in edge industrial applications, yet their deployment remains severely constrained by requirements for deterministic low latency and stable execution under resource limitations. Existing frameworks either rely on bloated general-purpose designs or force developers into opaque, hardware-specific closed-source ecosystems, leading to hardware lock-in limitation and poor cross-platform adaptability. Observing that modern AI agents can efficiently search and tune configurations to generate highly optimized low-level kernels for standard LLM operators, we propose EdgeFM, a lightweight, agent-driven VLM/LLM inference framework tailored for cross-platform industrial edge deployment. EdgeFM removes non-essential features to reduce single-request latency, and encapsulates agent-tuned kernel optimizations as a modular library of reusable skills. By allowing direct invocation of these skills rather than waiting for closed-source implementations, it effectively closes the performance gap long dominated by proprietary toolchains. The framework natively supports mainstream platforms including x86 and NVIDIA Orin SoCs, and represents the first end-to-end VLA deployment on the domestic Horizon Journey platform, enhancing cross-platform portability. In most cases, it yields clearly better inference performance than conventional vendor-specific toolchains, achieving up to 1.49 times speedup over TensorRT-Edge-LLM on the NVIDIA Orin platform. Experimental results show that EdgeFM delivers favorable end-to-end inference performance, providing an open-source, production-grade solution for diverse edge industrial scenarios.

Xiaojun Ye, Chun Wang, Yiren Song et al.

Movie Audio Description (AD) aims to narrate visual content during dialogue-free segments, particularly benefiting blind and visually impaired (BVI) audiences. Compared with general video captioning, AD demands plot-relevant narration with explicit character name references, posing unique challenges in movie understanding.To identify active main characters and focus on storyline-relevant regions, we propose FocusedAD, a novel framework that delivers character-centric movie audio descriptions. It includes: (i) a Character Perception Module(CPM) for tracking character regions and linking them to names; (ii) a Dynamic Prior Module(DPM) that injects contextual cues from prior ADs and subtitles via learnable soft prompts; and (iii) a Focused Caption Module(FCM) that generates narrations enriched with plot-relevant details and named characters. To overcome limitations in character identification, we also introduce an automated pipeline for building character query banks. FocusedAD achieves state-of-the-art performance on multiple benchmarks, including strong zero-shot results on MAD-eval-Named and our newly proposed Cinepile-AD dataset. Code and data will be released at https://github.com/Thorin215/FocusedAD .

Chun Wang, Xiaojun Ye, Xiaoran Pan et al.

Recent advances in Visual Language Models (VLMs) have demonstrated exceptional performance in visual reasoning tasks. However, geo-localization presents unique challenges, requiring the extraction of multigranular visual cues from images and their integration with external world knowledge for systematic reasoning. Current approaches to geo-localization tasks often lack robust reasoning mechanisms and explainability, limiting their effectiveness. To address these limitations, we propose the Geo Reason Enhancement (GRE) Suite, a novel framework that augments VLMs with structured reasoning chains for accurate and interpretable location inference. The GRE Suite is systematically developed across three key dimensions: dataset, model, and benchmark. First, we introduce GRE30K, a high-quality geo-localization reasoning dataset designed to facilitate fine-grained visual and contextual analysis. Next, we present the GRE model, which employs a multi-stage reasoning strategy to progressively infer scene attributes, local details, and semantic features, thereby narrowing down potential geographic regions with enhanced precision. Finally, we construct the Geo Reason Evaluation Benchmark (GREval-Bench), a comprehensive evaluation framework that assesses VLMs across diverse urban, natural, and landmark scenes to measure both coarse-grained (e.g., country, continent) and fine-grained (e.g., city, street) localization performance. Experimental results demonstrate that GRE significantly outperforms existing methods across all granularities of geo-localization tasks, underscoring the efficacy of reasoning-augmented VLMs in complex geographic inference. Code and data will be released at https://github.com/Thorin215/GRE.

Zixuan Gu, Qiufeng Fan, Long Sun et al.

With the advancement of Large Language Models (LLMs), LLM applications have expanded into a growing number of fields. However, users with data privacy concerns face limitations in directly utilizing LLM APIs, while private deployments incur significant computational demands. This creates a substantial challenge in achieving secure LLM adaptation under constrained local resources. To address this issue, collaborative learning methods, such as Split Learning (SL), offer a resource-efficient and privacy-preserving solution for adapting LLMs to private domains. In this study, we introduce VFLAIR-LLM (available at https://github.com/FLAIR-THU/VFLAIR-LLM), an extensible and lightweight split learning framework for LLMs, enabling privacy-preserving LLM inference and fine-tuning in resource-constrained environments. Our library provides two LLM partition settings, supporting three task types and 18 datasets. In addition, we provide standard modules for implementing and evaluating attacks and defenses. We benchmark 5 attacks and 9 defenses under various Split Learning for LLM(SL-LLM) settings, offering concrete insights and recommendations on the choice of model partition configurations, defense strategies, and relevant hyperparameters for real-world applications.

Xinmiao Hu, Chun Wang, Ruihe An et al.

Multimodal Large Language Models (MLLMs) have demonstrated strong performance in visual understanding tasks, yet they often suffer from object hallucinations--generating descriptions of objects that are inconsistent with or entirely absent from the input. This issue is closely related to dataset biases, where frequent co-occurrences of objects lead to entangled semantic representations across modalities. As a result, models may erroneously activate object representations that are commonly associated with the input but not actually present. To address this, we propose a causality-driven disentanglement framework that mitigates hallucinations through causal intervention. Our approach includes a Causal-Driven Projector in the visual pathway and a Causal Intervention Module integrated into the final transformer layer of the language model. These components work together to reduce spurious correlations caused by biased training data. Experimental results show that our method significantly reduces hallucinations while maintaining strong performance on multiple multimodal benchmarks. Visualization analyses further confirm improved separability of object representations. The code is available at: https://github.com/IgniSavium/Causal-LLaVA

Zheng Wang, Xiaojun Ye, Chaokun Wang et al.

Network embedding, aiming to project a network into a low-dimensional space, is increasingly becoming a focus of network research. Semi-supervised network embedding takes advantage of labeled data, and has shown promising performance. However, existing semi-supervised methods would get unappealing results in the completely-imbalanced label setting where some classes have no labeled nodes at all. To alleviate this, we propose two novel semi-supervised network embedding methods. The first one is a shallow method named RSDNE. Specifically, to benefit from the completely-imbalanced labels, RSDNE guarantees both intra-class similarity and inter-class dissimilarity in an approximate way. The other method is RECT which is a new class of graph neural networks. Different from RSDNE, to benefit from the completely-imbalanced labels, RECT explores the class-semantic knowledge. This enables RECT to handle networks with node features and multi-label setting. Experimental results on several real-world datasets demonstrate the superiority of the proposed methods. Code is available at https://github.com/zhengwang100/RECT.

Mingjin Chen, Junhao Chen, Xiaojun Ye et al.

3D human body reconstruction has been a challenge in the field of computer vision. Previous methods are often time-consuming and difficult to capture the detailed appearance of the human body. In this paper, we propose a new method called \emph{Ultraman} for fast reconstruction of textured 3D human models from a single image. Compared to existing techniques, \emph{Ultraman} greatly improves the reconstruction speed and accuracy while preserving high-quality texture details. We present a set of new frameworks for human reconstruction consisting of three parts, geometric reconstruction, texture generation and texture mapping. Firstly, a mesh reconstruction framework is used, which accurately extracts 3D human shapes from a single image. At the same time, we propose a method to generate a multi-view consistent image of the human body based on a single image. This is finally combined with a novel texture mapping method to optimize texture details and ensure color consistency during reconstruction. Through extensive experiments and evaluations, we demonstrate the superior performance of \emph{Ultraman} on various standard datasets. In addition, \emph{Ultraman} outperforms state-of-the-art methods in terms of human rendering quality and speed. Upon acceptance of the article, we will make the code and data publicly available.

Junhao Chen, Xiang Li, Xiaojun Ye et al.

With the success of 2D diffusion models, 2D AIGC content has already transformed our lives. Recently, this success has been extended to 3D AIGC, with state-of-the-art methods generating textured 3D models from single images or text. However, we argue that current 3D AIGC methods still do not fully unleash human creativity. We often imagine 3D content made from multimodal inputs, such as what it would look like if my pet bunny were eating a doughnut on the table. In this paper, we explore a novel 3D AIGC approach: generating 3D content from IDEAs. An IDEA is a multimodal input composed of text, image, and 3D models. To our knowledge, this challenging and exciting 3D AIGC setting has not been studied before. We propose the new framework Idea23D, which combines three agents based on large multimodal models (LMMs) and existing algorithmic tools. These three LMM-based agents are tasked with prompt generation, model selection, and feedback reflection. They collaborate and critique each other in a fully automated loop, without human intervention. The framework then generates a text prompt to create 3D models that align closely with the input IDEAs. We demonstrate impressive 3D AIGC results that surpass previous methods. To comprehensively assess the 3D AIGC capabilities of Idea23D, we introduce the Eval3DAIGC-198 dataset, containing 198 multimodal inputs for 3D generation tasks. This dataset evaluates the alignment between generated 3D content and input IDEAs. Our user study and quantitative results show that Idea23D significantly improves the success rate and accuracy of 3D generation, with excellent compatibility across various LMM, Text-to-Image, and Image-to-3D models. Code and dataset are available at \url{https://idea23d.github.io/}.

Mingjun Li, Xiaojun Ye

Which tasks inside an enterprise workflow can a large-language-model agent reliably handle, and under what conditions? Most business process modeling frameworks still answer this at the activity level, even though a single activity can bundle work of radically different difficulty. This paper takes the analysis a step smaller. We describe two design artifacts developed in a financial-services IT setting: T-IPO, which represents each task as an eight-element tuple, and LARA (LLM Agent Readiness Assessment), a five-dimension rubric that scores a task's readiness for agent substitution. Compliance Sensitivity carries $1.5\times$ weight, a value we fixed through a three-round Delphi study and cross-checked with AHP. The rubric produces four levels, L1 to L4, and applies a floor rule so that a task with maximum compliance load cannot be classified below L3 no matter what the other scores say. Both artifacts sit inside a larger methodology (PARTIS) that we map onto BWW ontology in Section 3. We evaluate the instruments across 127 tasks. Inter-rater agreement reaches Fleiss' $κ= 0.80$; a replication at three further institutions returns $κ= 0.73$. A controlled comparison against activity-level assessment suggests, though does not prove, an improvement in predictive utility at the task level. Pilot deployment of 120 task instances confirms that auto-completion decays monotonically from $95\%$ at L1 through about $70\%$ at L2 to about $40\%$ at L3. Exploratory factor analysis points to a two-factor structure: task readiness seems to be determined jointly by cognitive-execution complexity and governance-compliance intensity. We close with a recalibration procedure (LARA-TCA) so the rubric can keep pace with evolving LLM capabilities.

Yiren Song, Shijie Huang, Chen Yao et al.

The painting process of artists is inherently stepwise and varies significantly among different painters and styles. Generating detailed, step-by-step painting processes is essential for art education and research, yet remains largely underexplored. Traditional stroke-based rendering methods break down images into sequences of brushstrokes, yet they fall short of replicating the authentic processes of artists, with limitations confined to basic brushstroke modifications. Text-to-image models utilizing diffusion processes generate images through iterative denoising, also diverge substantially from artists' painting process. To address these challenges, we introduce ProcessPainter, a text-to-video model that is initially pre-trained on synthetic data and subsequently fine-tuned with a select set of artists' painting sequences using the LoRA model. This approach successfully generates painting processes from text prompts for the first time. Furthermore, we introduce an Artwork Replication Network capable of accepting arbitrary-frame input, which facilitates the controlled generation of painting processes, decomposing images into painting sequences, and completing semi-finished artworks. This paper offers new perspectives and tools for advancing art education and image generation technology.

Lin Sun, Xiaojun Ye, Jun Zhao et al.

Local differential privacy (LDP) has received much interest recently. In existing protocols with LDP guarantees, a user encodes and perturbs his data locally before sharing it to the aggregator. In common practice, however, users would prefer not to answer all the questions due to different privacy-preserving preferences for different questions, which leads to data missing or the loss of data quality. In this paper, we demonstrate a new approach for addressing the challenges of data perturbation with consideration of users' privacy preferences. Specifically, we first propose BiSample: a bidirectional sampling technique value perturbation in the framework of LDP. Then we combine the BiSample mechanism with users' privacy preferences for missing data perturbation. Theoretical analysis and experiments on a set of datasets confirm the effectiveness of the proposed mechanisms.

Zheng Wang, Qiao Wang, Tingzhang Zhao et al.

Feature selection, an effective technique for dimensionality reduction, plays an important role in many machine learning systems. Supervised knowledge can significantly improve the performance. However, faced with the rapid growth of newly emerging concepts, existing supervised methods might easily suffer from the scarcity and validity of labeled data for training. In this paper, the authors study the problem of zero-shot feature selection (i.e., building a feature selection model that generalizes well to "unseen" concepts with limited training data of "seen" concepts). Specifically, they adopt class-semantic descriptions (i.e., attributes) as supervision for feature selection, so as to utilize the supervised knowledge transferred from the seen concepts. For more reliable discriminative features, they further propose the center-characteristic loss which encourages the selected features to capture the central characteristics of seen concepts. Extensive experiments conducted on various real-world datasets demonstrate the effectiveness of the method.

Lin Sun, Jun Zhao, Xiaojun Ye et al.

Local differential privacy (LDP) has been deemed as the de facto measure for privacy-preserving distributed data collection and analysis. Recently, researchers have extended LDP to the basic data type in NoSQL systems: the key-value data, and show its feasibilities in mean estimation and frequency estimation. In this paper, we develop a set of new perturbation mechanisms for key-value data collection and analysis under the strong model of local differential privacy. Since many modern machine learning tasks rely on the availability of conditional probability or the marginal statistics, we then propose the conditional frequency estimation method for key analysis and the conditional mean estimation for value analysis in key-value data. The released statistics with conditions can further be used in learning tasks. Extensive experiments of frequency and mean estimation on both synthetic and real-world datasets validate the effectiveness and accuracy of the proposed key-value perturbation mechanisms against the state-of-art competitors.

Lin Sun, Jun Zhao, Xiaojun Ye

Clustering and analyzing on collected data can improve user experiences and quality of services in big data, IoT applications. However, directly releasing original data brings potential privacy concerns, which raises challenges and opportunities for privacy-preserving clustering. In this paper, we study the problem of non-interactive clustering in distributed setting under the framework of local differential privacy. We first extend the Bit Vector, a novel anonymization mechanism to be functionality-capable and privacy-preserving. Based on the modified encoding mechanism, we propose kCluster algorithm that can be used for clustering in the anonymized space. We show the modified encoding mechanism can be easily implemented in existing clustering algorithms that only rely on distance information, such as DBSCAN. Theoretical analysis and experimental results validate the effectiveness of the proposed schemes.

Qiao Wang, Zheng Wang, Xiaojun Ye

LINE [1], as an efficient network embedding method, has shown its effectiveness in dealing with large-scale undirected, directed, and/or weighted networks. Particularly, it proposes to preserve both the local structure (represented by First-order Proximity) and global structure (represented by Second-order Proximity) of the network. In this study, we prove that LINE with these two proximities (LINE(1st) and LINE(2nd)) are actually factoring two different matrices separately. Specifically, LINE(1st) is factoring a matrix M (1), whose entries are the doubled Pointwise Mutual Information (PMI) of vertex pairs in undirected networks, shifted by a constant. LINE(2nd) is factoring a matrix M (2), whose entries are the PMI of vertex and context pairs in directed networks, shifted by a constant. We hope this finding would provide a basis for further extensions and generalizations of LINE.