arXiv subjects

Wenjie Zhang

Publications and source records attributed to Wenjie Zhang.

At least 109 records · Page 6Linked to original sources

arXiv2025

SGPT: Few-Shot Prompt Tuning for Signed Graphs

Signed Graph Neural Networks (SGNNs) are effective in learning expressive representations for signed graphs but typically require substantial task-specific labels, limiting their applicability in label-scarce industrial scenarios. In contrast, unsigned graph structures are abundant and can be readily leveraged to pre-train Graph Neural Networks (GNNs), offering a promising solution to reduce supervision requirements in downstream signed graph tasks. However, transferring knowledge from unsigned to signed graphs is non-trivial due to the fundamental discrepancies in graph types and task objectives between pre-training and downstream phases. To address this challenge, we propose Signed Graph Prompt Tuning (SGPT), a novel graph prompting framework that adapts pre-trained unsigned GNNs to few-shot signed graph tasks. We first design a graph template based on balance theory to disentangle mixed node relationships introduced by negative links, mitigating the structural mismatches between unsigned and signed graphs. We further introduce a task template that reformulates downstream signed tasks into a unified link prediction objective, aligning their optimization goals with the pre-training task. Furthermore, we develop feature prompts that align downstream semantic spaces with the feature spaces learned during pre-training, and semantic prompts to integrate link sign semantics in a task-aware manner. We conduct extensive experiments on seven benchmark signed graph datasets, demonstrating that SGPT significantly outperforms existing state-of-the-art methods, establishing a powerful and generalizable solution for few-shot signed graph learning.

cs.LG↗

arXiv2025

Ovis2.5 Technical Report

We present Ovis2.5, a successor to Ovis2 designed for native-resolution visual perception and strong multimodal reasoning. Ovis2.5 integrates a native-resolution vision transformer that processes images at their native, variable resolutions, avoiding the degradation from fixed-resolution tiling and preserving both fine detail and global layout -- crucial for visually dense content like complex charts. To strengthen reasoning, we train the model to move beyond linear chain-of-thought and perform reflection -- including self-checking and revision. This advanced capability is exposed as an optional "thinking mode" at inference time, allowing users to trade latency for enhanced accuracy on difficult inputs. The model is trained via a comprehensive five-phase curriculum that progressively builds its skills. The process begins with foundational visual and multimodal pretraining, advances through large-scale instruction tuning, and culminates in alignment and reasoning enhancement using DPO and GRPO. To scale these upgrades efficiently, we employ multimodal data packing and hybrid parallelism, yielding a significant end-to-end speedup. We release two open-source models: Ovis2.5-9B and Ovis2.5-2B. The latter continues the "small model, big performance" philosophy of Ovis2, making it ideal for resource-constrained, on-device scenarios. On the OpenCompass multimodal leaderboard, Ovis2.5-9B averages 78.3, marking a substantial improvement over its predecessor, Ovis2-8B, and achieving state-of-the-art results among open-source MLLMs in the sub-40B parameter range; Ovis2.5-2B scores 73.9, establishing SOTA for its size. Beyond aggregate scores, Ovis2.5 achieves leading results on STEM benchmarks, exhibits strong capabilities on grounding and video tasks, and achieves open-source SOTA at its scale for complex chart analysis.

cs.CV↗

arXiv2025

Empowering Tabular Data Preparation with Language Models: Why and How?

Data preparation is a critical step in enhancing the usability of tabular data and thus boosts downstream data-driven tasks. Traditional methods often face challenges in capturing the intricate relationships within tables and adapting to the tasks involved. Recent advances in Language Models (LMs), especially in Large Language Models (LLMs), offer new opportunities to automate and support tabular data preparation. However, why LMs suit tabular data preparation (i.e., how their capabilities match task demands) and how to use them effectively across phases still remain to be systematically explored. In this survey, we systematically analyze the role of LMs in enhancing tabular data preparation processes, focusing on four core phases: data acquisition, integration, cleaning, and transformation. For each phase, we present an integrated analysis of how LMs can be combined with other components for different preparation tasks, highlight key advancements, and outline prospective pipelines.

cs.AI↗

arXiv2025

Unlocking Multi-Modal Potentials for Link Prediction on Dynamic Text-Attributed Graphs

Dynamic Text-Attributed Graphs (DyTAGs) are a novel graph paradigm that captures evolving temporal events (edges) alongside rich textual attributes. Existing studies can be broadly categorized into TGNN-driven and LLM-driven approaches, both of which encode textual attributes and temporal structures for DyTAG representation. We observe that DyTAGs inherently comprise three distinct modalities: temporal, textual, and structural, often exhibiting completely disjoint distributions. However, the first two modalities are largely overlooked by existing studies, leading to suboptimal performance. To address this, we propose MoMent, a multi-modal model that explicitly models, integrates, and aligns each modality to learn node representations for link prediction. Given the disjoint nature of the original modality distributions, we first construct modality-specific features and encode them using individual encoders to capture correlations across temporal patterns, semantic context, and local structures. Each encoder generates modality-specific tokens, which are then fused into comprehensive node representations with a theoretical guarantee. To avoid disjoint subspaces of these heterogeneous modalities, we propose a dual-domain alignment loss that first aligns their distributions globally and then fine-tunes coherence at the instance level. This enhances coherent representations from temporal, textual, and structural views. Extensive experiments across seven datasets show that MoMent achieves up to 17.28% accuracy improvement and up to 31x speed-up against eight baselines.

cs.LG↗

arXiv2025

Do They Understand Them? An Updated Evaluation on Nonbinary Pronoun Handling in Large Language Models

Large language models (LLMs) are increasingly deployed in sensitive contexts where fairness and inclusivity are critical. Pronoun usage, especially concerning gender-neutral and neopronouns, remains a key challenge for responsible AI. Prior work, such as the MISGENDERED benchmark, revealed significant limitations in earlier LLMs' handling of inclusive pronouns, but was constrained to outdated models and limited evaluations. In this study, we introduce MISGENDERED+, an extended and updated benchmark for evaluating LLMs' pronoun fidelity. We benchmark five representative LLMs, GPT-4o, Claude 4, DeepSeek-V3, Qwen Turbo, and Qwen2.5, across zero-shot, few-shot, and gender identity inference. Our results show notable improvements compared with previous studies, especially in binary and gender-neutral pronoun accuracy. However, accuracy on neopronouns and reverse inference tasks remains inconsistent, underscoring persistent gaps in identity-sensitive reasoning. We discuss implications, model-specific observations, and avenues for future inclusive AI research.

cs.CL↗

arXiv2025

WOCD: A Semi-Supervised Method for Overlapping Community Detection Using Weak Cliques

Overlapping community detection (OCD) is a fundamental graph data analysis task for extracting graph patterns. Traditional OCD methods can be broadly divided into node clustering and link clustering approaches, both of which rely solely on link information to identify overlapping communities. In recent years, deep learning-based methods have made significant advancements for this task. However, existing GNN-based approaches often face difficulties in effectively integrating link, attribute, and prior information, along with challenges like limited receptive fields and over-smoothing, which hinder their performance on complex overlapping community detection. In this paper, we propose a Weak-clique based Overlapping Community Detection method, namely WOCD, which incorporates prior information and optimizes the use of link information to improve detection accuracy. Specifically, we introduce pseudo-labels within a semi-supervised framework to strengthen the generalization ability, making WOCD more versatile. Furthermore, we initialize pseudo-labels using weak cliques to fully leverage link and prior information, leading to better detection accuracy. Additionally, we employ a single-layer Graph Transformer combined with GNN, which achieves significant performance improvements while maintaining efficiency. We evaluate WOCD on eight real-world attributed datasets, and the results demonstrate that it outperforms the state-of-the-art semi-supervised OCD method by a significant margin in terms of accuracy.

cs.SI↗

arXiv2025

LogLite: Lightweight Plug-and-Play Streaming Log Compression

Log data is a vital resource for capturing system events and states. With the increasing complexity and widespread adoption ofmodern software systems and IoT devices, the daily volume of log generation has surged to tens of petabytes, leading to significant collection and storage costs. To address this challenge, lossless log compression has emerged as an effective solution, enabling substantial resource savings without compromising log information. In this paper, we first conduct a characterization study on extensive public log datasets and identify four key observations. Building on these insights, we propose LogLite, a lightweight, plug-and-play, streaming lossless compression algorithm designed to handle both TEXT and JSON logs throughout their life cycle. LogLite requires no predefined rules or pre-training and is inherently adaptable to evolving log structures. Our evaluation shows that, compared to state-of-the-art baselines, LogLite achieves Pareto optimality in most scenarios, delivering an average improvement of up to 67.8% in compression ratio and up to 2.7 $\times$ in compression speed.

cs.DB↗

arXiv2025

Non-Hermitian topological electric circuits with projective symmetry

Non-Hermitian topological insulators have attracted considerable attention due to their distinctive energy band characteristics and promising applications. Here, we systematically investigate non-Hermitian Möbius insulators and graphene-like topological semimetals from the projected symmetry and realize their corresponding topological phenomena in an electric circuit-based framework. By introducing a nonreciprocal hopping term consisting of negative impedance converters into a two-dimensional electric circuit, we establish an experimental platform that effectively demonstrates that introducing non-Hermitian terms significantly enhances the energy localization of topological edge states, which originate from the non-Hermitian skin effect. Furthermore, a thorough comparison of experimental measurements with numerical simulations validates the robustness and reliability of our electric circuit structure. This work not only reveals the physical properties of non-Hermitian topological materials but also provides valuable theoretical and experimental guidance for the implementation of topological circuits and the design of radiofrequency devices in the future.

cond-mat.mes-hall↗

arXiv2025

ProbDiffFlow: An Efficient Learning-Free Framework for Probabilistic Single-Image Optical Flow Estimation

This paper studies optical flow estimation, a critical task in motion analysis with applications in autonomous navigation, action recognition, and film production. Traditional optical flow methods require consecutive frames, which are often unavailable due to limitations in data acquisition or real-world scene disruptions. Thus, single-frame optical flow estimation is emerging in the literature. However, existing single-frame approaches suffer from two major limitations: (1) they rely on labeled training data, making them task-specific, and (2) they produce deterministic predictions, failing to capture motion uncertainty. To overcome these challenges, we propose ProbDiffFlow, a training-free framework that estimates optical flow distributions from a single image. Instead of directly predicting motion, ProbDiffFlow follows an estimation-by-synthesis paradigm: it first generates diverse plausible future frames using a diffusion-based model, then estimates motion from these synthesized samples using a pre-trained optical flow model, and finally aggregates the results into a probabilistic flow distribution. This design eliminates the need for task-specific training while capturing multiple plausible motions. Experiments on both synthetic and real-world datasets demonstrate that ProbDiffFlow achieves superior accuracy, diversity, and efficiency, outperforming existing single-image and two-frame baselines.

cs.CV↗

arXiv2025

LLM-based HSE Compliance Assessment: Benchmark, Performance, and Advancements

Health, Safety, and Environment (HSE) compliance assessment demands dynamic real-time decision-making under complicated regulations and complex human-machine-environment interactions. While large language models (LLMs) hold significant potential for decision intelligence and contextual dialogue, their capacity for domain-specific knowledge in HSE and structured legal reasoning remains underexplored. We introduce HSE-Bench, the first benchmark dataset designed to evaluate the HSE compliance assessment capabilities of LLM. HSE-Bench comprises over 1,000 manually curated questions drawn from regulations, court cases, safety exams, and fieldwork videos, and integrates a reasoning flow based on Issue spotting, rule Recall, rule Application, and rule Conclusion (IRAC) to assess the holistic reasoning pipeline. We conduct extensive evaluations on different prompting strategies and more than 10 LLMs, including foundation models, reasoning models and multimodal vision models. The results show that, although current LLMs achieve good performance, their capabilities largely rely on semantic matching rather than principled reasoning grounded in the underlying HSE compliance context. Moreover, their native reasoning trace lacks the systematic legal reasoning required for rigorous HSE compliance assessment. To alleviate these, we propose a new prompting technique, Reasoning of Expert (RoE), which guides LLMs to simulate the reasoning process of different experts for compliance assessment and reach a more accurate unified decision. We hope our study highlights reasoning gaps in LLMs for HSE compliance and inspires further research on related tasks.

cs.CL↗

arXiv2025

OSS-UAgent: An Agent-based Usability Evaluation Framework for Open Source Software

Usability evaluation is critical to the impact and adoption of open source software (OSS), yet traditional methods relying on human evaluators suffer from high costs and limited scalability. To address these limitations, we introduce OSS-UAgent, an automated, configurable, and interactive agent-based usability evaluation framework specifically designed for open source software. Our framework employs intelligent agents powered by large language models (LLMs) to simulate developers performing programming tasks across various experience levels (from Junior to Expert). By dynamically constructing platform-specific knowledge bases, OSS-UAgent ensures accurate and context-aware code generation. The generated code is automatically evaluated across multiple dimensions, including compliance, correctness, and readability, providing a comprehensive measure of the software's usability. Additionally, our demonstration showcases OSS-UAgent's practical application in evaluating graph analytics platforms, highlighting its effectiveness in automating usability evaluation.

cs.SE↗

arXiv2025

QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning

This paper addresses the inherent inference latency challenges associated with deploying multimodal large language models (MLLM) in quadruped vision-language-action (QUAR-VLA) tasks. Our investigation reveals that conventional parameter reduction techniques ultimately impair the performance of the language foundation model during the action instruction tuning phase, making them unsuitable for this purpose. We introduce a novel latency-free quadruped MLLM model, dubbed QUART-Online, designed to enhance inference efficiency without degrading the performance of the language foundation model. By incorporating Action Chunk Discretization (ACD), we compress the original action representation space, mapping continuous action values onto a smaller set of discrete representative vectors while preserving critical information. Subsequently, we fine-tune the MLLM to integrate vision, language, and compressed actions into a unified semantic space. Experimental results demonstrate that QUART-Online operates in tandem with the existing MLLM system, achieving real-time inference in sync with the underlying controller frequency, significantly boosting the success rate across various tasks by 65%. Our project page is https://quart-online.github.io.

cs.RO↗

arXiv2025

DARWIN 1.5: Large Language Models as Materials Science Adapted Learners

Materials discovery and design aim to find compositions and structures with desirable properties over highly complex and diverse physical spaces. Traditional solutions, such as high-throughput simulations or machine learning, often rely on complex descriptors, which hinder generalizability and transferability across different material systems. Moreover, These descriptors may inadequately represent macro-scale material properties, which are influenced by structural imperfections and compositional variations in real-world samples, thus limiting their practical applicability. To address these challenges, we propose DARWIN 1.5, the largest open-source large language model tailored for materials science. By leveraging natural language as input, DARWIN eliminates the need for task-specific descriptors and enables a flexible, unified approach to material property prediction and discovery. Our approach integrates 6M material domain papers and 21 experimental datasets from 49,256 materials across modalities while enabling cross-task knowledge transfer. The enhanced model achieves up to 59.1% improvement in prediction accuracy over the base LLaMA-7B architecture and outperforms SOTA machine learning approaches across 8 materials design tasks. These results establish LLMs as a promising foundation for developing versatile and scalable models in materials science.

cs.CL↗

arXiv2025

Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model

Knowledge in materials science is widely dispersed across extensive scientific literature, posing significant challenges to the efficient discovery and integration of new materials. Traditional methods, often reliant on costly and time-consuming experimental approaches, further complicate rapid innovation. Addressing these challenges, the integration of artificial intelligence with materials science has opened avenues for accelerating the discovery process, though it also demands precise annotation, data extraction, and traceability of information. To tackle these issues, this article introduces the Materials Knowledge Graph (MKG), which utilizes advanced natural language processing techniques integrated with large language models to extract and systematically organize a decade's worth of high-quality research into structured triples, contains 162,605 nodes and 731,772 edges. MKG categorizes information into comprehensive labels such as Name, Formula, and Application, structured around a meticulously designed ontology, thus enhancing data usability and integration. By implementing network-based algorithms, MKG not only facilitates efficient link prediction but also significantly reduces reliance on traditional experimental methods. This structured approach not only streamlines materials research but also lays the groundwork for more sophisticated science knowledge graphs.

cs.CL↗

arXiv2025

Counterfactual Inference for Eliminating Sentiment Bias in Recommender Systems

Recommender Systems (RSs) aim to provide personalized recommendations for users. A newly discovered bias, known as sentiment bias, uncovers a common phenomenon within Review-based RSs (RRSs): the recommendation accuracy of users or items with negative reviews deteriorates compared with users or items with positive reviews. Critical users and niche items are disadvantaged by such unfair recommendations. We study this problem from the perspective of counterfactual inference with two stages. At the model training stage, we build a causal graph and model how sentiment influences the final rating score. During the inference stage, we decouple the direct and indirect effects to mitigate the impact of sentiment bias and remove the indirect effect using counterfactual inference. We have conducted extensive experiments, and the results validate that our model can achieve comparable performance on rating prediction for better recommendations and effective mitigation of sentiment bias. To the best of our knowledge, this is the first work to employ counterfactual inference on sentiment bias mitigation in RSs.

cs.IR↗

arXiv2025

Efficient Computation of Hyper-triangles on Hypergraphs

Hypergraphs, which use hyperedges to capture groupwise interactions among different entities, have gained increasing attention recently for their versatility in effectively modeling real-world networks. In this paper, we study the problem of computing hyper-triangles (formed by three fully-connected hyperedges), which is a basic structural unit in hypergraphs. Although existing approaches can be adopted to compute hyper-triangles by exhaustively examining hyperedge combinations, they overlook the structural characteristics distinguishing different hyper-triangle patterns. Consequently, these approaches lack specificity in computing particular hyper-triangle patterns and exhibit low efficiency. In this paper, we unveil a new formation pathway for hyper-triangles, transitioning from hyperedges to hyperwedges before assembling into hyper-triangles, and classify hyper-triangle patterns based on hyperwedges. Leveraging this insight, we introduce a two-step framework to reduce the redundant checking of hyperedge combinations. Under this framework, we propose efficient algorithms for computing a specific pattern of hyper-triangles. Approximate algorithms are also devised to support estimated counting scenarios. Furthermore, we introduce a fine-grained hypergraph clustering coefficient measurement that can reflect diverse properties of hypergraphs based on different hyper-triangle patterns. Extensive experimental evaluations conducted on 11 real-world datasets validate the effectiveness and efficiency of our proposed techniques.

cs.DS↗

arXiv2025

Optimizing Large Model Training through Overlapped Activation Recomputation

Large model training often uses recomputation to alleviate memory pressure and pipelines to exploit the parallelism of data, tensors, and devices. However, existing recomputation approaches may incur high overhead when training real-world models, as they are executed on demand in the critical training path. In this paper, we present Lynx, a new recomputation framework to reduce overhead by overlapping recomputation with communication in training pipelines. To reduce the large search space for recomputation strategies, we propose a heuristic-based recomputation scheduling algorithm, which is based on the observation that there are identical structures in large DNN models so that we can apply the same scheduling policy to all such structures. Additionally, we propose a recomputation-aware model partitioning method to balance each stage's execution time for improved training throughput. Our comprehensive evaluation using GPT models with 1.3B-23B parameters shows that Lynx outperforms existing recomputation approaches by up to 1.37x.

cs.DC↗

arXiv2025

Motif Counting in Complex Networks: A Comprehensive Survey

Motif counting plays a crucial role in understanding the structural properties of networks. By computing motif frequencies, researchers can draw key insights into the structural properties of the underlying network. As networks become increasingly complex, different graph models have been proposed, giving rise to diverse motif patterns. These variations introduce unique computational challenges that require specialized algorithms tailored to specific motifs within different graph structures. This survey provides a comprehensive and structured overview of motif counting techniques across general graphs, heterogeneous graphs, and hypergraphs. We categorize existing algorithms according to their underlying computational strategies, emphasizing key similarities and distinctions. In addition to reviewing current methodologies, we examine their strengths, limitations, and computational trade-offs. Furthermore, we explore future directions in motif counting, including scalable implementations to improve efficiency in large-scale networks, algorithmic adaptations for dynamic, temporal, and attributed graphs, and deeper integration with large language models (LLMs) and graph-based retrieval-augmented generation (GraphRAG). By offering a detailed analysis of these approaches, this survey aims to support researchers and practitioners in advancing motif counting for increasingly complex network data.

cs.SI↗